Instructions to use Locutusque/TinyMistral-248M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/TinyMistral-248M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/TinyMistral-248M-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/TinyMistral-248M-Instruct")
model = AutoModelForCausalLM.from_pretrained("Locutusque/TinyMistral-248M-Instruct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Locutusque/TinyMistral-248M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/TinyMistral-248M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/TinyMistral-248M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/TinyMistral-248M-Instruct

SGLang

How to use Locutusque/TinyMistral-248M-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 "Locutusque/TinyMistral-248M-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": "Locutusque/TinyMistral-248M-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 "Locutusque/TinyMistral-248M-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": "Locutusque/TinyMistral-248M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/TinyMistral-248M-Instruct with Docker Model Runner:
```
docker model run hf.co/Locutusque/TinyMistral-248M-Instruct
```

Locutusque commited on Dec 3, 2023

Commit

32a9317

1 Parent(s): 43380ec

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ inference:
     top_p: 0.34
     top_k: 30
     max_new_tokens: 250
-    repetition_penalty: 1.15
 ---
 Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
 It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.

     top_p: 0.34
     top_k: 30
     max_new_tokens: 250
+    repetition_penalty: 1.18
 ---
 Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
 It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.