Instructions to use fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL with Transformers:

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

pipe = pipeline("text-generation", model="fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL")
model = AutoModelForCausalLM.from_pretrained("fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL

SGLang

How to use fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL 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 "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL" \
    --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": "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL",
		"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 "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL" \
        --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": "fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL with Docker Model Runner:
```
docker model run hf.co/fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL
```

CQoT_MATH_Llama-3.2-3B-v7.6-FINAL / README.md

fc91

Upload README.md with huggingface_hub

bfbdc6f verified 8 months ago

preview code

Raw

History Blame Contribute Delete

616 Bytes

metadata

base_model: fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
license: apache-2.0
language:
  - en

Uploaded model

Developed by: fc91
License: apache-2.0
Finetuned from model : fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7

This llama model was trained 2x faster with Unsloth