Instructions to use Andyrasika/mistral-ft-optimized-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Andyrasika/mistral-ft-optimized-dpo with Transformers:

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

pipe = pipeline("text-generation", model="Andyrasika/mistral-ft-optimized-dpo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Andyrasika/mistral-ft-optimized-dpo")
model = AutoModelForCausalLM.from_pretrained("Andyrasika/mistral-ft-optimized-dpo")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Andyrasika/mistral-ft-optimized-dpo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Andyrasika/mistral-ft-optimized-dpo

SGLang

How to use Andyrasika/mistral-ft-optimized-dpo 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 "Andyrasika/mistral-ft-optimized-dpo" \
    --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": "Andyrasika/mistral-ft-optimized-dpo",
		"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 "Andyrasika/mistral-ft-optimized-dpo" \
        --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": "Andyrasika/mistral-ft-optimized-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Andyrasika/mistral-ft-optimized-dpo with Docker Model Runner:
```
docker model run hf.co/Andyrasika/mistral-ft-optimized-dpo
```

Andyrasika commited on Feb 5, 2024

Commit

c1fc88b

verified ·

1 Parent(s): d18b82b

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -8,6 +8,8 @@ language:
 - en
 metrics:
 - accuracy
 ---
 # Model Card for Model ID
@@ -25,11 +27,6 @@ metrics:
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** Ankush Singal
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
 - **Finetuned from model [optional]:** https://huggingface.co/OpenPipe/mistral-ft-optimized-1227

 - en
 metrics:
 - accuracy
+datasets:
+- jondurbin/truthy-dpo-v0.1
 ---
 # Model Card for Model ID
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** Ankush Singal
 - **Finetuned from model [optional]:** https://huggingface.co/OpenPipe/mistral-ft-optimized-1227