Instructions to use EmbeddedLLM/Mistral-7B-Merge-14-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Mistral-7B-Merge-14-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0.2")
model = AutoModelForCausalLM.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0.2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/Mistral-7B-Merge-14-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/Mistral-7B-Merge-14-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2

SGLang

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.2 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 "EmbeddedLLM/Mistral-7B-Merge-14-v0.2" \
    --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0.2",
		"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 "EmbeddedLLM/Mistral-7B-Merge-14-v0.2" \
        --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.2 with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Update 2023-12-19

In light of dataset contamination issue among the merged models raised by the community in recent days, in particular berkeley-nest/Starling-LM-7B-alpha, Q-bert/MetaMath-Cybertron-Starling, and janai-hq/trinity-v1, we decided to remake another model without the models mentioned. Additionally, their CC-by-NC-4.0 license is restrictive and thus are not suitable for an open model.

Open LLM Leaderboard

For reference, this model obtained an average score of 72.88.

Average	72.88
ARC	68.86
HellaSwag	87.01
MMLU	65.05
TruthfulQA	64.19
Winogrande	81.69
GSM8K	70.51

Model Description

This is an experiment to test merging 14 models using DARE TIES 🦙

The merged model is then merged again with janai-hq/trinity-v1 using Gradient SLERP. The result is a base model that performs quite well but requires some further instruction fine-tuning.

The 14 models are as follows:

base model: mistralai/Mistral-7B-v0.1

The yaml config file for this model is here:

slices:
  - sources:
      - model: janai-hq/trinity-v1
        layer_range: [0, 32]
      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0
        layer_range: [0, 32]
merge_method: slerp
base_model: janai-hq/trinity-v1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Downloads last month: 95

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for EmbeddedLLM/Mistral-7B-Merge-14-v0.2

Base model

EmbeddedLLM/Mistral-7B-Merge-14-v0

Finetuned

(2)

this model

Merges

9 models

Quantizations

1 model