Instructions to use gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help with Transformers:

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

pipe = pipeline("text-generation", model="gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help")
model = AutoModelForCausalLM.from_pretrained("gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help

SGLang

How to use gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help 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 "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help" \
    --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": "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help",
		"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 "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help" \
        --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": "gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help with Docker Model Runner:
```
docker model run hf.co/gate369/TinyMistral-248Mx4-MOE-not-tuned-pls-help
```

TinyMistral-248Mx4-MOE-not-tuned-pls-help / mergekit_moe_config.yml

limin(gate)

Upload folder using huggingface_hub

4610e3f verified over 2 years ago

Raw

History Blame Contribute Delete

1.54 kB


	base_model: Locutusque/TinyMistral-248M-v2-Instruct
	gate_mode: hidden
	dtype: bfloat16
	experts:
	- source_model: M4-ai/TinyMistral-248M-v2-cleaner
	positive_prompts:
	- "versatile"
	- "helpful"
	- "factual"
	- "integrated"
	- "adaptive"
	- "comprehensive"
	- "balanced"
	negative_prompts:
	- "specialized"
	- "narrow"
	- "focused"
	- "limited"
	- "specific"

	- source_model: Locutusque/TinyMistral-248M-Instruct
	positive_prompts:
	- "creative"
	- "chat"
	- "discuss"
	- "culture"
	- "world"
	- "expressive"
	- "detailed"
	- "imaginative"
	- "engaging"
	negative_prompts:
	- "sorry"
	- "cannot"
	- "factual"
	- "concise"
	- "straightforward"
	- "objective"
	- "dry"

	- source_model: jtatman/tinymistral-v2-pycoder-instuct-248m
	positive_prompts:
	- "analytical"
	- "accurate"
	- "logical"
	- "knowledgeable"
	- "precise"
	- "calculate"
	- "compute"
	- "solve"
	- "work"
	- "python"
	- "javascript"
	- "programming"
	- "algorithm"
	- "tell me"
	- "assistant"
	negative_prompts:
	- "creative"
	- "abstract"
	- "imaginative"
	- "artistic"
	- "emotional"
	- "mistake"
	- "inaccurate"

	- source_model: Locutusque/TinyMistral-248M-v2-Instruct
	positive_prompts:
	- "instructive"
	- "clear"
	- "directive"
	- "helpful"
	- "informative"
	negative_prompts:
	- "exploratory"
	- "open-ended"
	- "narrative"
	- "speculative"
	- "artistic"