Instructions to use xinchen9/llama3-b8-ft-dis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xinchen9/llama3-b8-ft-dis with Transformers:

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

pipe = pipeline("text-generation", model="xinchen9/llama3-b8-ft-dis")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xinchen9/llama3-b8-ft-dis")
model = AutoModelForCausalLM.from_pretrained("xinchen9/llama3-b8-ft-dis")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xinchen9/llama3-b8-ft-dis with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xinchen9/llama3-b8-ft-dis"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xinchen9/llama3-b8-ft-dis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xinchen9/llama3-b8-ft-dis

SGLang

How to use xinchen9/llama3-b8-ft-dis 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 "xinchen9/llama3-b8-ft-dis" \
    --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": "xinchen9/llama3-b8-ft-dis",
		"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 "xinchen9/llama3-b8-ft-dis" \
        --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": "xinchen9/llama3-b8-ft-dis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xinchen9/llama3-b8-ft-dis with Docker Model Runner:
```
docker model run hf.co/xinchen9/llama3-b8-ft-dis
```

1. Model Details

Introducing xinchen9/llama3-b8-ft, an advanced language model comprising 8 billion parameters. It has been fine-trained based on Meta-Llama-3-8.

There are two steps: 1:The llama3-b8 model was fine-tuning on dataset SlimOrca. 2: With CoT distillation.

2. How to Use

Here give some examples of how to use our model.

Text Completion

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "deepseek-ai/deepseek-llm-7b-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

3 Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	13.85
IFEval (0-Shot)	15.46
BBH (3-Shot)	24.73
MATH Lvl 5 (4-Shot)	3.17
GPQA (0-shot)	8.39
MuSR (0-shot)	6.41
MMLU-PRO (5-shot)	24.93

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F32

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

15.460
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

24.730
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

3.170
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

8.390
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

6.410
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

24.930