YanoljaNEXT EEVE 10.8B

313

90

10.8B

llama

by

yanolja

Language Model

OTHER

10.8B params

New

313 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

25GB+ RAM

Mobile

Laptop

Server

Quick Summary

If you're passionate about the field of Large Language Models and wish to exchange knowledge and insights, we warmly invite you to join our Discord server.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

11GB+ RAM

Code Examples

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Kpython

# number_of_old_tokens is the size of tokenizer before vocab extension. For example, in case of EEVE-Korean-10.8B-v1.0, number_of_old_tokens is 32000.
def freeze_partial_embedding_hook(grad):
    grad[:number_of_old_tokens] = 0
    return grad

for name, param in model.named_parameters():
    if ("lm_head" in name or "embed_tokens" in name) and "original" not in name:
        param.requires_grad = True
        if "embed_tokens" in name:
            param.register_hook(freeze_partial_embedding_hook)
    else:
        param.requires_grad = False

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.