Instructions to use YeonwooSung/mistral-7b-cot-neftune-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YeonwooSung/mistral-7b-cot-neftune-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="YeonwooSung/mistral-7b-cot-neftune-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YeonwooSung/mistral-7b-cot-neftune-v0.1")
model = AutoModelForCausalLM.from_pretrained("YeonwooSung/mistral-7b-cot-neftune-v0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YeonwooSung/mistral-7b-cot-neftune-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YeonwooSung/mistral-7b-cot-neftune-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YeonwooSung/mistral-7b-cot-neftune-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YeonwooSung/mistral-7b-cot-neftune-v0.1

SGLang

How to use YeonwooSung/mistral-7b-cot-neftune-v0.1 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 "YeonwooSung/mistral-7b-cot-neftune-v0.1" \
    --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": "YeonwooSung/mistral-7b-cot-neftune-v0.1",
		"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 "YeonwooSung/mistral-7b-cot-neftune-v0.1" \
        --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": "YeonwooSung/mistral-7b-cot-neftune-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YeonwooSung/mistral-7b-cot-neftune-v0.1 with Docker Model Runner:
```
docker model run hf.co/YeonwooSung/mistral-7b-cot-neftune-v0.1
```

Model Card for Model ID

The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. This model uses peft finetuning with NEFTune for robustness.

Model Details

Model Description

This model is a finetuned model of the mistralai/Mistral-7B-v0.1.

Training Details

Training Data

This model is finetuned with kaist-ai/CoT-Collection.

Training Procedure

This model trained with SFT trainer and NEFTune method. (According to the paper, NEFTune adds noise to the embedding vectors during training)

Training Hyperparameters

lora alpha: 16
lora r: 64
lora dropout: 0.05
max sequence length: 4096
learning rate: 2e-4
max_grad_norm: 0.3
weight_decay: 0.001
gradient checkpoint: True
optim: paged_adamw_32bit
use_bf16: True
use_4bit: True
use_nested_quant: False
bnb_4bit_compute_dtype: float16
bnb_4bit_quant_type: nf4

Downloads last month: 15

Safetensors

Model size

7B params

Tensor type

F32

F16

Paper for YeonwooSung/mistral-7b-cot-neftune-v0.1

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14