Instructions to use jtatman/TinyMistral-248m-v2.5-4x-Moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/TinyMistral-248m-v2.5-4x-Moe with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/TinyMistral-248m-v2.5-4x-Moe")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jtatman/TinyMistral-248m-v2.5-4x-Moe")
model = AutoModelForCausalLM.from_pretrained("jtatman/TinyMistral-248m-v2.5-4x-Moe")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jtatman/TinyMistral-248m-v2.5-4x-Moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/TinyMistral-248m-v2.5-4x-Moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/TinyMistral-248m-v2.5-4x-Moe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jtatman/TinyMistral-248m-v2.5-4x-Moe

SGLang

How to use jtatman/TinyMistral-248m-v2.5-4x-Moe 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 "jtatman/TinyMistral-248m-v2.5-4x-Moe" \
    --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": "jtatman/TinyMistral-248m-v2.5-4x-Moe",
		"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 "jtatman/TinyMistral-248m-v2.5-4x-Moe" \
        --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": "jtatman/TinyMistral-248m-v2.5-4x-Moe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jtatman/TinyMistral-248m-v2.5-4x-Moe with Docker Model Runner:
```
docker model run hf.co/jtatman/TinyMistral-248m-v2.5-4x-Moe
```

TinyMistral-248m-v2.5-4x-Moe

TinyMistral-248m-v2.5-4x-Moe is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

🧩 Configuration

base_model: Locutusque/TinyMistral-248M-v2.5-Instruct
experts:
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "Write me a Python program that calculates the factorial of n."
      - "Help me debug this code."
      - "Optimize this C++ program."
    negative_prompts:
      - "How do you"
      - "Explain the concept of"
      - "Give an overview of"
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
      - "Craft me a list of some nice places to visit around the world."
      - "Write me a story"
      - "Write me an essay"
      - "How do I incorporate visual elements into my writing?"
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "What is the product of 2 x 5 x 18?"
      - "How do I guess the value of x for the function f(x) = x^4 - 2x^2 - 1?"
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Assist me with writing a program that"
      - "Craft me a list of some nice places to visit around the world. "
      - "Write me a story"
      - "Write me an essay"
      - "How do I incorporate visual elements into my writing?"
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "How do I incorporate fewer visual elements into my art but retain impact?"
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
      - "Craft me a list of some nice places to visit around the world. "
      - "Write me a story"
      - "Write me an essay"
  - source_model: jtatman/tinymistral-samantha-chatml-lora-v2
    positive_prompts:
      - "Craft me a list of some nice places to visit around the world. "
      - "Write me a story"
      - "Write me an essay"
      - "Create a fantasy story about"
      - "Tell me about the wild fjords."
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
      - "How do I incorporate visual elements into my writing?"
gate_mode: hidden

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jtatman/TinyMistral-248m-v2.5-4x-Moe"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 4

Safetensors

Model size

0.7B params

Tensor type

F32

Model tree for jtatman/TinyMistral-248m-v2.5-4x-Moe

Locutusque/TinyMistral-248M-v2.5-Instruct

jtatman/tinymistral-samantha-chatml-lora-v2

Merge model

this model