Instructions to use DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1")
model = AutoModelForCausalLM.from_pretrained("DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1

SGLang

How to use DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1 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 "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1" \
    --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": "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1",
		"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 "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1" \
        --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": "DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1 with Docker Model Runner:
```
docker model run hf.co/DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1
```

ChatAllInOne_Mixtral-8x7B-v1

Description

ChatAllInOne_Mixtral-8x7B-v1 is a chat language model fine-tuned on the CHAT-ALL-IN-ONE-v1 dataset using the QLoRA technique. Originally based on the mistralai/Mixtral-8x7B-Instruct-v0.1 model, this version is specifically optimized for diverse and comprehensive chat applications.

Model Details

Base Model: mistralai/Mixtral-8x7B-Instruct-v0.1
Fine-tuning Technique: QLoRA
Dataset: CHAT-ALL-IN-ONE-v1
Tool Used for Fine-tuning: Axolotl

Features

Enhanced understanding and generation of conversational language.
Improved performance in diverse chat scenarios, including casual, formal, and domain-specific conversations.
Fine-tuned to maintain context and coherence over longer dialogues.

Prompt Format

Vicuna 1.1

See the finetuning dataset for examples.

License

This model is open-sourced under the Apache 2.0 License. See the LICENSE file for more details.

Discord Server

Join our Discord server here.

Feeling Generous? 😊

Eager to buy me a cup of 2$ coffe or iced tea?🍵☕ Sure, here is the link: https://ko-fi.com/drnicefellow. Please add a note on which one you want me to drink?

Downloads last month: 822

Dataset used to train DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1

Collection including DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1

ChatAllInOne

Collection

4 items • Updated Apr 6, 2025 • 2