Instructions to use Vezora/Mistral-29b-Merge-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vezora/Mistral-29b-Merge-Base with Transformers:

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

pipe = pipeline("text-generation", model="Vezora/Mistral-29b-Merge-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vezora/Mistral-29b-Merge-Base")
model = AutoModelForCausalLM.from_pretrained("Vezora/Mistral-29b-Merge-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Vezora/Mistral-29b-Merge-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vezora/Mistral-29b-Merge-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vezora/Mistral-29b-Merge-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vezora/Mistral-29b-Merge-Base

SGLang

How to use Vezora/Mistral-29b-Merge-Base 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 "Vezora/Mistral-29b-Merge-Base" \
    --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": "Vezora/Mistral-29b-Merge-Base",
		"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 "Vezora/Mistral-29b-Merge-Base" \
        --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": "Vezora/Mistral-29b-Merge-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vezora/Mistral-29b-Merge-Base with Docker Model Runner:
```
docker model run hf.co/Vezora/Mistral-29b-Merge-Base
```

Contributors: Nicolas Mejia Petit

Mistral 29b: A New Base Model

The objective of this model is to serve as a new fully open source base model with 29.2 billion parameters.

This model spits out jargon, and needs to be fine tuned, either with qlora, with the adapter attached to every layer, or better yet a full fine tune.

Model Creation

The model was created by stacking four models: Dolphin, Zephyr, Meta-math7b, and Speechless code, to form a single model.

Useful Resources

Model Merging (MergeKit) (https://github.com/cg123/mergekit)

Source Models

Dolphin2.1-mistral-7b by Eric Hartford (https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
Zephyr-7b-beta by HuggingFace (https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
MetaMath-Mistral-7B by meta-math (https://huggingface.co/meta-math/MetaMath-Mistral-7B)
speechless-code-mistral-7b-v1.0 (https://huggingface.co/uukuguy/speechless-code-mistral-7b-v1.0)

Downloads last month: 12

Safetensors

Model size

28B params

Tensor type

BF16