Instructions to use Vezora/Mistral-14b-Merge-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vezora/Mistral-14b-Merge-Base with Transformers:

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

pipe = pipeline("text-generation", model="Vezora/Mistral-14b-Merge-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vezora/Mistral-14b-Merge-Base")
model = AutoModelForCausalLM.from_pretrained("Vezora/Mistral-14b-Merge-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Vezora/Mistral-14b-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-14b-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-14b-Merge-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vezora/Mistral-14b-Merge-Base

SGLang

How to use Vezora/Mistral-14b-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-14b-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-14b-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-14b-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-14b-Merge-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vezora/Mistral-14b-Merge-Base with Docker Model Runner:
```
docker model run hf.co/Vezora/Mistral-14b-Merge-Base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Contributors: Nicolas Mejia Petit

Mistral 14b: A New Base Model

The objective of this model is to serve as a fully open source new base model with 14.3 billion parameters. It has been enhanced with a LoRa adapter attached to all 62 layers of the merged model. The model is capable of generating outputs and responding accurately to inputs. However, it tends to over-respond with unasked questions when asked to process more than 512 tokens, which is its training limit using QLoRa.

With full fine-tuning, this model has the potential to deliver excellent performance.

Qlora adapter was trained on a modified dataset of airoboros-m-7b-3.1.2, using SFT. In the Alpaca Format.

Model Creation

The model was created by merging two models: Dolphin and Zephyr, along with Meta-math7b and Speechless code, to form a single model. The layers of these two models were stacked on top of each other to create this model.

Initially, the output from the model was pure jargon. To rectify this, a LoRa adapter was trained and merged across all layers.

Useful Resources

LoRa Adapter Merging (https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930)
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)
Airoboros-m-7b-3.1.2 (https://huggingface.co/jondurbin/airoboros-m-7b-3.1.2)

upcoming Mistral 30b

We currently have a Mistral model with 29 billion parameters(29.2B params) in development. At present, the model's output is not yet refined and may appear as jargon. If there is interest in the community for fine-tuning this model, we are open to uploading it in its current state. Otherwise, we plan to complete our training process before making it available. You can let us know with a post in this repo's discussion's!

Downloads last month: 231

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for Vezora/Mistral-14b-Merge-Base

Quantizations

1 model