Instructions to use duffels/dolphin-2.6-mistral-7b-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use duffels/dolphin-2.6-mistral-7b-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="duffels/dolphin-2.6-mistral-7b-exl2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("duffels/dolphin-2.6-mistral-7b-exl2")
model = AutoModelForCausalLM.from_pretrained("duffels/dolphin-2.6-mistral-7b-exl2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use duffels/dolphin-2.6-mistral-7b-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "duffels/dolphin-2.6-mistral-7b-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duffels/dolphin-2.6-mistral-7b-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/duffels/dolphin-2.6-mistral-7b-exl2

SGLang

How to use duffels/dolphin-2.6-mistral-7b-exl2 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 "duffels/dolphin-2.6-mistral-7b-exl2" \
    --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": "duffels/dolphin-2.6-mistral-7b-exl2",
		"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 "duffels/dolphin-2.6-mistral-7b-exl2" \
        --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": "duffels/dolphin-2.6-mistral-7b-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use duffels/dolphin-2.6-mistral-7b-exl2 with Docker Model Runner:
```
docker model run hf.co/duffels/dolphin-2.6-mistral-7b-exl2
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

ORIGINAL MODEL: cognitivecomputations/dolphin-2.6-mistral-7b

I take requests - you can either check my profile for my contacts or add me on Discord - my username is duffels

This repo is just my collection of dolphin-2.6-7b exl2 conversions. I noticed there weren't any readily available here on HF.

Refer to the table below or post in the community tab up top if you have any questions about the naming scheme

File Name	Explanation
dm7b-v2.6-exl2-Q4	4-Bit Quantization

Downloads last month: 11