Instructions to use lejelly/ties-mistral-7b-instrcut-math-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lejelly/ties-mistral-7b-instrcut-math-code with Transformers:

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

pipe = pipeline("text-generation", model="lejelly/ties-mistral-7b-instrcut-math-code")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lejelly/ties-mistral-7b-instrcut-math-code")
model = AutoModelForCausalLM.from_pretrained("lejelly/ties-mistral-7b-instrcut-math-code")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lejelly/ties-mistral-7b-instrcut-math-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lejelly/ties-mistral-7b-instrcut-math-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lejelly/ties-mistral-7b-instrcut-math-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lejelly/ties-mistral-7b-instrcut-math-code

SGLang

How to use lejelly/ties-mistral-7b-instrcut-math-code 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 "lejelly/ties-mistral-7b-instrcut-math-code" \
    --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": "lejelly/ties-mistral-7b-instrcut-math-code",
		"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 "lejelly/ties-mistral-7b-instrcut-math-code" \
        --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": "lejelly/ties-mistral-7b-instrcut-math-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lejelly/ties-mistral-7b-instrcut-math-code with Docker Model Runner:
```
docker model run hf.co/lejelly/ties-mistral-7b-instrcut-math-code
```

ties

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

# Ties
# Each parameter refers to TIES-MERGING Appendix C.4 [https://arxiv.org/abs/2306.01708] 
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      density: 0.2
      weight: 1.0
  - model: TIGER-Lab/MAmmoTH2-7B
    parameters:
      density: 0.2
      weight: 1.0
  - model: Nondzu/Mistral-7B-codealpaca-lora
    parameters:
      density: 0.2
      weight: 1.0
merge_method: ties
parameters:
  normalize: false
  lambda: 1.0
dtype: float16
tokenizer:
  source: union

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

F16

Model tree for lejelly/ties-mistral-7b-instrcut-math-code

Nondzu/Mistral-7B-codealpaca-lora

TIGER-Lab/MAmmoTH2-7B

mistralai/Mistral-7B-Instruct-v0.2

mistralai/Mistral-7B-v0.1

Merge model

this model

Paper for lejelly/ties-mistral-7b-instrcut-math-code

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19