Instructions to use MedinaArmando/llama-3.2-1b-cfr-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MedinaArmando/llama-3.2-1b-cfr-merged with Transformers:

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

pipe = pipeline("text-generation", model="MedinaArmando/llama-3.2-1b-cfr-merged")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MedinaArmando/llama-3.2-1b-cfr-merged")
model = AutoModelForCausalLM.from_pretrained("MedinaArmando/llama-3.2-1b-cfr-merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MedinaArmando/llama-3.2-1b-cfr-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MedinaArmando/llama-3.2-1b-cfr-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MedinaArmando/llama-3.2-1b-cfr-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MedinaArmando/llama-3.2-1b-cfr-merged

SGLang

How to use MedinaArmando/llama-3.2-1b-cfr-merged 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 "MedinaArmando/llama-3.2-1b-cfr-merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MedinaArmando/llama-3.2-1b-cfr-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "MedinaArmando/llama-3.2-1b-cfr-merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MedinaArmando/llama-3.2-1b-cfr-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MedinaArmando/llama-3.2-1b-cfr-merged with Docker Model Runner:
```
docker model run hf.co/MedinaArmando/llama-3.2-1b-cfr-merged
```

Up and running in Hugging Face Space using 2 virtual cpu's and 16 GB RAM!! CFR-FineTuned_III

Llama-3.2-1B Fine-tuned on the Code of Federal Regulations (CFR)

This is a fine-tuned version of meta-llama/Meta-Llama-3.2-1B trained on all sections from the United States Code of Federal Regulations (CFR). The goal: provide a specialized assistant for navigating and answering questions about U.S. federal regulations.

Model Description

Base Model: Llama-3.2-1B
Method: QLoRA, 4-bit quantization
Dataset: Custom, parsed from CFR XML (Titles 1-50)
Epochs: 3
Tokens Seen: ~243M
Final Training Loss: 1.267
Mean Token Accuracy: 0.739
Training Time: ~5h 17m

Hardware/Environment:
Training was conducted on Modal using a single NVIDIA H200 GPU.
Training speed: ~1.10 steps/sec, 35 samples/sec.

Note: This loss is typical for a Llama-3 1B model on legal/complex text. For comparison: random output would yield >2.0; perfect memorization of a small dataset would yield <1.0. This is in the “actually learned something useful” range for this setup.

Intended Uses & Limitations

Intended Uses

Regulatory Q&A
Summarization of CFR text
Text generation related to U.S. federal regulations

Limitations

NOT a substitute for legal advice. Output may be incorrect or outdated (data as of 2024-06-25).
Can hallucinate—don’t trust answers without checking against the source.
Validation/test loss is not reported here (evaluate on your own task/data before using in production).

How to Use

You can use this model directly with the transformers library.

Downloads last month: 14

Safetensors

Model size

1B params

Tensor type

F32