Instructions to use Norquinal/Mistral-7B-claude-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norquinal/Mistral-7B-claude-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Norquinal/Mistral-7B-claude-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norquinal/Mistral-7B-claude-instruct")
model = AutoModelForCausalLM.from_pretrained("Norquinal/Mistral-7B-claude-instruct", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norquinal/Mistral-7B-claude-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Norquinal/Mistral-7B-claude-instruct

SGLang

How to use Norquinal/Mistral-7B-claude-instruct 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 "Norquinal/Mistral-7B-claude-instruct" \
    --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": "Norquinal/Mistral-7B-claude-instruct",
		"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 "Norquinal/Mistral-7B-claude-instruct" \
        --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": "Norquinal/Mistral-7B-claude-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Norquinal/Mistral-7B-claude-instruct with Docker Model Runner:
```
docker model run hf.co/Norquinal/Mistral-7B-claude-instruct
```

Adding Evaluation Results

by leaderboard-pr-bot - opened Nov 17, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+14

-1

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -40,4 +40,17 @@ Or, alternatively, change `model_type` in `config.json` from `mistral` to `llama
 >
 >In summary, these five technologies have deeply altered our lives and created new possibilities, yet they come with tradeoffs and ethical dilemmas. Continued innovation and collaboration between industry, academia and governments will be needed to ensure these technologies fulfill their promises while minimizing unforeseen consequences.
 >
->I hope this provides some helpful insights! Let me know if you would like me to expand on any specific points.

 >
 >In summary, these five technologies have deeply altered our lives and created new possibilities, yet they come with tradeoffs and ethical dilemmas. Continued innovation and collaboration between industry, academia and governments will be needed to ensure these technologies fulfill their promises while minimizing unforeseen consequences.
 >
+>I hope this provides some helpful insights! Let me know if you would like me to expand on any specific points.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Norquinal__Mistral-7B-claude-instruct)
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 51.71   |
+| ARC (25-shot)         | 63.23          |
+| HellaSwag (10-shot)   | 84.99    |
+| MMLU (5-shot)         | 63.84         |
+| TruthfulQA (0-shot)   | 47.47   |
+| Winogrande (5-shot)   | 78.14   |
+| GSM8K (5-shot)        | 17.97        |
+| DROP (3-shot)         | 6.35         |