Text Generation
Transformers
Safetensors
English
mixtral
Mixture of Experts
Merge
text-generation-inference
Instructions to use Kquant03/PygWin-4x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kquant03/PygWin-4x7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kquant03/PygWin-4x7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Kquant03/PygWin-4x7B") model = AutoModelForCausalLM.from_pretrained("Kquant03/PygWin-4x7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Kquant03/PygWin-4x7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kquant03/PygWin-4x7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kquant03/PygWin-4x7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Kquant03/PygWin-4x7B
- SGLang
How to use Kquant03/PygWin-4x7B 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/PygWin-4x7B" \ --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/PygWin-4x7B", "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/PygWin-4x7B" \ --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/PygWin-4x7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Kquant03/PygWin-4x7B with Docker Model Runner:
docker model run hf.co/Kquant03/PygWin-4x7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,16 +2,16 @@
|
|
| 2 |
license: llama2
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/
|
| 6 |
tags:
|
| 7 |
- moe
|
| 8 |
- merge
|
| 9 |
---
|
| 10 |
|
| 11 |
-

|
| 15 |
|
| 16 |
[Join our Discord!](https://discord.gg/uT4CzytfYW)
|
| 17 |
|
|
|
|
| 2 |
license: llama2
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/qC7TRZv2B1w4MD65KHkH4.png"
|
| 6 |
tags:
|
| 7 |
- moe
|
| 8 |
- merge
|
| 9 |
---
|
| 10 |
|
| 11 |
+

|
| 12 |
|
| 13 |
# Experimental frankenMoE of Pygmalion and Xwin
|
| 14 |
+
[FP16 GGUF HERE](https://huggingface.co/Kquant03/PygWin-4x7B-FP16-GGUF)
|
| 15 |
|
| 16 |
[Join our Discord!](https://discord.gg/uT4CzytfYW)
|
| 17 |
|