Qwen3-14B-ft-limo

6

14.0B

license:apache-2.0

by

mrm8488

Other

OTHER

14B params

New

0 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

32GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

14GB+ RAM

Code Examples

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

For non thinking as it is trained for thinking by default (LIMO)pythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "mrm8488/Qwen3-14B-ft-limo"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Solve (x + 2)^2 = 0."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # Disable thinking as it is trained for thinking by default
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

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.