Instructions to use OuteAI/Lite-Mistral-150M-v2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OuteAI/Lite-Mistral-150M-v2-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="OuteAI/Lite-Mistral-150M-v2-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Mistral-150M-v2-Instruct")
model = AutoModelForCausalLM.from_pretrained("OuteAI/Lite-Mistral-150M-v2-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OuteAI/Lite-Mistral-150M-v2-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OuteAI/Lite-Mistral-150M-v2-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OuteAI/Lite-Mistral-150M-v2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OuteAI/Lite-Mistral-150M-v2-Instruct

SGLang

How to use OuteAI/Lite-Mistral-150M-v2-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 "OuteAI/Lite-Mistral-150M-v2-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OuteAI/Lite-Mistral-150M-v2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "OuteAI/Lite-Mistral-150M-v2-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OuteAI/Lite-Mistral-150M-v2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OuteAI/Lite-Mistral-150M-v2-Instruct with Docker Model Runner:
```
docker model run hf.co/OuteAI/Lite-Mistral-150M-v2-Instruct
```

edwko commited on Jul 18, 2024

Commit

25f3b6b

verified ·

1 Parent(s): 841b905

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -16,6 +16,18 @@ The model was trained on ~8 billion tokens.
 - Extended Training: Further refinement of the model, resulting in improved benchmark performance and overall text generation quality.
 - Tokenizer changes.
 ## How coherent is the 150M model?
 Let's look at real-world examples:
@@ -132,18 +144,6 @@ The model shows some promise in understanding context related to simple requests
   </tr>
 </table>
-## Chat format
-This model uses a specific chat format for optimal performance.
-```
-<s>system
-[System message]</s>
-<s>user
-[Your question or message]</s>
-<s>assistant
-[The model's response]</s>
-```
 ## Usage with HuggingFace transformers
 The model can be used with HuggingFace's `transformers` library:
 ```python

 - Extended Training: Further refinement of the model, resulting in improved benchmark performance and overall text generation quality.
 - Tokenizer changes.
+## Chat format
+This model is **very sensitive** to the chat template used. Ensure you use the correct template:
+```
+<s>system
+[System message]</s>
+<s>user
+[Your question or message]</s>
+<s>assistant
+[The model's response]</s>
+```
 ## How coherent is the 150M model?
 Let's look at real-world examples:
   </tr>
 </table>
 ## Usage with HuggingFace transformers
 The model can be used with HuggingFace's `transformers` library:
 ```python