Instructions to use llleb/mistral-7b-arc-qlora-exp7-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llleb/mistral-7b-arc-qlora-exp7-3 with Transformers:

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

pipe = pipeline("text-generation", model="llleb/mistral-7b-arc-qlora-exp7-3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llleb/mistral-7b-arc-qlora-exp7-3")
model = AutoModelForCausalLM.from_pretrained("llleb/mistral-7b-arc-qlora-exp7-3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llleb/mistral-7b-arc-qlora-exp7-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llleb/mistral-7b-arc-qlora-exp7-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llleb/mistral-7b-arc-qlora-exp7-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/llleb/mistral-7b-arc-qlora-exp7-3

SGLang

How to use llleb/mistral-7b-arc-qlora-exp7-3 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 "llleb/mistral-7b-arc-qlora-exp7-3" \
    --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": "llleb/mistral-7b-arc-qlora-exp7-3",
		"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 "llleb/mistral-7b-arc-qlora-exp7-3" \
        --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": "llleb/mistral-7b-arc-qlora-exp7-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llleb/mistral-7b-arc-qlora-exp7-3 with Docker Model Runner:
```
docker model run hf.co/llleb/mistral-7b-arc-qlora-exp7-3
```

mistral-7b-arc-qlora-exp7-3 / README.md

llleb

Update README.md

7015fb5 verified 2 months ago

preview code

Raw

History Blame Contribute Delete

688 Bytes

metadata

base_model: mistralai/Mistral-7B-v0.1
library_name: transformers
pipeline_tag: text-generation
tags:
  - qlora
  - arc-challenge
  - mistral
  - science-qa

mistral-7b-arc-qlora-exp7-3

This model is a QLoRA task-adapted Mistral-7B-v0.1 model for ARC-Challenge science multiple-choice QA.

Training setup

Base model: mistralai/Mistral-7B-v0.1
Method: 4-bit NF4 QLoRA + response-only loss
Training data: ARC-Challenge train, ARC-Easy train subset, OpenBookQA train
ARC-Easy ratio: 0.3
Learning rate: 3e-05
Epochs: 4
LoRA r/alpha/dropout: 64 / 128 / 0.05

Evaluation

Evaluated with lm-evaluation-harness on arc_challenge using 25-shot prompting.