Instructions to use prithivMLmods/QwQ-LCoT-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/QwQ-LCoT-3B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/QwQ-LCoT-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/QwQ-LCoT-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/QwQ-LCoT-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/QwQ-LCoT-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/QwQ-LCoT-3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/QwQ-LCoT-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/QwQ-LCoT-3B-Instruct

SGLang

How to use prithivMLmods/QwQ-LCoT-3B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/QwQ-LCoT-3B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/QwQ-LCoT-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/QwQ-LCoT-3B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/QwQ-LCoT-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/QwQ-LCoT-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/QwQ-LCoT-3B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

QwQ-LCoT-3B-Instruct Model Card

The QwQ-LCoT-3B-Instruct model is a lightweight, instruction-tuned language model designed for complex reasoning and explanation tasks. It is fine-tuned on the Qwen2.5-3B-Instruct base model using the QwQ-LongCoT-130K dataset, focusing on long-chain-of-thought (LCoT) reasoning for enhanced logical comprehension and detailed output generation.

File Name	Size	Description	Upload Status
`.gitattributes`	1.57 kB	Specifies LFS tracking for large files.	Uploaded
`README.md`	267 Bytes	Basic project information file.	Updated
`added_tokens.json`	657 Bytes	Custom tokens added to the tokenizer.	Uploaded
`config.json`	859 Bytes	Configuration file for the model.	Uploaded
`generation_config.json`	281 Bytes	Configuration file for text generation settings.	Uploaded
`merges.txt`	1.82 MB	Contains the byte-pair encoding (BPE) merges.	Uploaded
`pytorch_model-00001-of-00002.bin`	4.96 GB	First shard of the model weights in PyTorch format.	Uploaded (LFS)
`pytorch_model-00002-of-00002.bin`	1.21 GB	Second shard of the model weights in PyTorch format.	Uploaded (LFS)
`pytorch_model.bin.index.json`	36 kB	Index mapping for sharded model weights.	Uploaded
`special_tokens_map.json`	644 Bytes	Maps special tokens to their roles.	Uploaded
`tokenizer.json`	11.4 MB	Serialized tokenizer data.	Uploaded (LFS)
`tokenizer_config.json`	7.73 kB	Tokenizer configuration settings.	Uploaded
`vocab.json`	2.78 MB	Vocabulary file for the tokenizer.	Uploaded

Sample Long CoT:

Key Features:

Long Chain-of-Thought Reasoning:
- Specifically designed to generate comprehensive, step-by-step explanations for complex queries.
Lightweight and Efficient:
- With only 3 billion parameters, it is optimized for systems with limited computational resources without compromising reasoning capabilities.
Instruction Optimization:
- Fine-tuned to follow prompts and provide concise, actionable, and structured responses.

Training Details:

Base Model: Qwen2.5-3B-Instruct
Dataset: amphora/QwQ-LongCoT-130K
- Comprising 133,000 annotated samples focusing on logical tasks and structured thinking.

Capabilities:

Text Generation:
- Provides detailed, structured, and logical text outputs tailored to user prompts.
Reasoning Tasks:
- Solves step-by-step problems in math, logic, and science.
Educational Assistance:
- Generates coherent explanations for academic and research purposes.
Dialogue and Summarization:
- Handles conversational queries and summarizes long documents effectively.

Usage Instructions:

Setup: Download all model files and ensure compatibility with the Hugging Face Transformers library.

Loading the Model:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/QwQ-LCoT-3B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Generate Long-Chain Reasoning Outputs:

input_text = "Explain the process of photosynthesis step-by-step."
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=300, temperature=0.5)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Customize Output Generation:
Modify the generation_config.json file for different scenarios:
- temperature: Controls randomness (lower = deterministic, higher = creative).
- max_length: Sets response length.
- top_p: Adjusts sampling for diversity in outputs.