lfm2-tiny-random

47

1.2B

—

by

yujiepan

Language Model

OTHER

1.2B params

New

47 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

3GB+ RAM

Mobile

Laptop

Server

Quick Summary

This tiny model is for debugging.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

2GB+ RAM

Code Examples

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Example usage:pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model_id = "yujiepan/lfm2-tiny-random"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="bfloat16",
    trust_remote_code=True,
    #    attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate answer
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_new_tokens=512,
)

print(tokenizer.decode(output[0], skip_special_tokens=False))

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

Codes to create this repo:pythontransformers

import json
from pathlib import Path

import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoProcessor,
    GenerationConfig,
    set_seed,
)

source_model_id = "LiquidAI/LFM2-1.2B"
save_folder = "/tmp/yujiepan/lfm2-tiny-random"

processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)

with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
    config_json = json.load(f)
config_json['block_dim'] = 64
config_json['block_ff_dim'] = 128
config_json['full_attn_idxs'] = [1]
config_json['conv_dim'] = 64
config_json['conv_dim_out'] = 64
config_json['hidden_size'] = 64
config_json['intermediate_size'] = 128
config_json['num_attention_heads'] = 2
config_json['num_heads'] = 2
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 1
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
    json.dump(config_json, f, indent=2)

config = AutoConfig.from_pretrained(
    save_folder,
    trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
    model.generation_config = GenerationConfig.from_pretrained(
        source_model_id, trust_remote_code=True,
    )
set_seed(42)
model = model.cpu()  # cpu is more stable for random initialization across machines
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.2)
        print(name, p.shape)
model.save_pretrained(save_folder)
print(model)

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.