Instructions to use EstherXC/mixtral_task_arithmetic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EstherXC/mixtral_task_arithmetic with Transformers:

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

pipe = pipeline("text-generation", model="EstherXC/mixtral_task_arithmetic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EstherXC/mixtral_task_arithmetic")
model = AutoModelForCausalLM.from_pretrained("EstherXC/mixtral_task_arithmetic", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EstherXC/mixtral_task_arithmetic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/EstherXC/mixtral_task_arithmetic

SGLang

How to use EstherXC/mixtral_task_arithmetic 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 "EstherXC/mixtral_task_arithmetic" \
    --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": "EstherXC/mixtral_task_arithmetic",
		"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 "EstherXC/mixtral_task_arithmetic" \
        --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": "EstherXC/mixtral_task_arithmetic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EstherXC/mixtral_task_arithmetic with Docker Model Runner:
```
docker model run hf.co/EstherXC/mixtral_task_arithmetic
```

mixtral_task_arithmetic / README.md

EstherXC

Upload folder using huggingface_hub

991b18f verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

1.19 kB

metadata

base_model:
  - mistralai/Mistral-7B-v0.1
  - EstherXC/mixtral_7b_protein_pretrain
  - wanglab/mixtral_7b_dna_pretrain
library_name: transformers
tags:
  - mergekit
  - merge

mixtral_task_arithmetic

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic 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:

base_model: mistralai/Mistral-7B-v0.1
models:
  - model: EstherXC/mixtral_7b_protein_pretrain
    parameters:
      weight: 0.3
  - model: wanglab/mixtral_7b_dna_pretrain #dnagpt/llama-dna
    parameters:
      weight: 0.3
merge_method: task_arithmetic
dtype: float16
tokenizer_source: "base"