Instructions to use datatune/llama-7b-logicot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datatune/llama-7b-logicot with Transformers:

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

pipe = pipeline("text-generation", model="datatune/llama-7b-logicot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("datatune/llama-7b-logicot")
model = AutoModelForCausalLM.from_pretrained("datatune/llama-7b-logicot")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use datatune/llama-7b-logicot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datatune/llama-7b-logicot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datatune/llama-7b-logicot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/datatune/llama-7b-logicot

SGLang

How to use datatune/llama-7b-logicot 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 "datatune/llama-7b-logicot" \
    --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": "datatune/llama-7b-logicot",
		"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 "datatune/llama-7b-logicot" \
        --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": "datatune/llama-7b-logicot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use datatune/llama-7b-logicot with Docker Model Runner:
```
docker model run hf.co/datatune/llama-7b-logicot
```

This model is tuned on the LogiCoT data and the GPT-4 alpaca data with the LLaMa-7b model.

We use 2 A100 GPUs

We first instruction-tuning LLaMa-7b on the GPT-4 alpaca data for 3 days, then on the LogiCoT data for 4 days.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	39.37
ARC (25-shot)	47.01
HellaSwag (10-shot)	72.56
MMLU (5-shot)	38.93
TruthfulQA (0-shot)	43.63
Winogrande (5-shot)	67.56
GSM8K (5-shot)	0.0
DROP (3-shot)	5.92

Downloads last month: 13

Safetensors

Model size

7B params

Tensor type

F32

datatune
/

llama-7b-logicot

Open LLM Leaderboard Evaluation Results

Dataset used to train datatune/llama-7b-logicot

Spaces using datatune/llama-7b-logicot 29