Instructions to use Kquant03/MistralTrix-4x9B-MoE-ERP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kquant03/MistralTrix-4x9B-MoE-ERP with Transformers:

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

pipe = pipeline("text-generation", model="Kquant03/MistralTrix-4x9B-MoE-ERP")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kquant03/MistralTrix-4x9B-MoE-ERP")
model = AutoModelForCausalLM.from_pretrained("Kquant03/MistralTrix-4x9B-MoE-ERP", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kquant03/MistralTrix-4x9B-MoE-ERP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kquant03/MistralTrix-4x9B-MoE-ERP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/MistralTrix-4x9B-MoE-ERP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kquant03/MistralTrix-4x9B-MoE-ERP

SGLang

How to use Kquant03/MistralTrix-4x9B-MoE-ERP 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 "Kquant03/MistralTrix-4x9B-MoE-ERP" \
    --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": "Kquant03/MistralTrix-4x9B-MoE-ERP",
		"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 "Kquant03/MistralTrix-4x9B-MoE-ERP" \
        --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": "Kquant03/MistralTrix-4x9B-MoE-ERP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kquant03/MistralTrix-4x9B-MoE-ERP with Docker Model Runner:
```
docker model run hf.co/Kquant03/MistralTrix-4x9B-MoE-ERP
```

Kquant03 commited on Jan 6, 2024

Commit

49431d8

1 Parent(s): 4dbfe54

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 # A model for ERP, engineered to bring you the most desirable experience.
 I finally figured out how to quantize FrankenMoE properly, so prepare for a flood of GGUF models from me. This one is scripted to be into whatever you're planning to do to it.
 # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
 ### (from the MistralAI papers...click the quoted question above to navigate to it directly.)

 # A model for ERP, engineered to bring you the most desirable experience.
 I finally figured out how to quantize FrankenMoE properly, so prepare for a flood of GGUF models from me. This one is scripted to be into whatever you're planning to do to it.
+Special thanks to [Cultrix](https://huggingface.co/CultriX) for the [base model](https://huggingface.co/CultriX/MistralTrix-v1).
 # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
 ### (from the MistralAI papers...click the quoted question above to navigate to it directly.)