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", device_map="auto")

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
```

TinyMistral-248M-Instruct / README.md

Locutusque

Update README.md

c463b0a over 2 years ago

1.82 kB

pipeline_tag: text-generation
base_model: Locutusque/TinyMistral-248M
license: apache-2.0
datasets:
  - Locutusque/InstructMixCleaned
  - berkeley-nest/Nectar
language:
  - en
widget:
  - text: >-
      <|USER|> Design a Neo4j database and Cypher function snippet to Display
      Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners.
      Implement if/else or switch/case statements to handle different conditions
      related to the Consent. Provide detailed comments explaining your control
      flow and the reasoning behind each decision. <|ASSISTANT|> 
  - text: '<|USER|> Write me a story about a magical place. <|ASSISTANT|> '
  - text: >-
      <|USER|> Write me an essay about the life of George Washington
      <|ASSISTANT|> 
  - text: '<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> '
  - text: >-
      <|USER|> Craft me a list of some nice places to visit around the world.
      <|ASSISTANT|> 
  - text: >-
      <|USER|> How to manage a lazy employee: Address the employee verbally.
      Don't allow an employee's laziness or lack of enthusiasm to become a
      recurring issue. Tell the employee you're hoping to speak with them about
      workplace expectations and performance, and schedule a time to sit down
      together. Question: To manage a lazy employee, it is suggested to talk to
      the employee. True, False, or Neither? <|ASSISTANT|> 
inference:
  parameters:
    temperature: 0.8
    do_sample: true
    top_p: 0.14
    top_k: 41
    max_new_tokens: 250
    repetition_penalty: 1.176

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.