Instructions to use QuixiAI/laserxtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuixiAI/laserxtral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuixiAI/laserxtral")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("QuixiAI/laserxtral") model = AutoModelForCausalLM.from_pretrained("QuixiAI/laserxtral", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use QuixiAI/laserxtral with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuixiAI/laserxtral" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuixiAI/laserxtral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/QuixiAI/laserxtral
- SGLang
How to use QuixiAI/laserxtral 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 "QuixiAI/laserxtral" \ --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": "QuixiAI/laserxtral", "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 "QuixiAI/laserxtral" \ --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": "QuixiAI/laserxtral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use QuixiAI/laserxtral with Docker Model Runner:
docker model run hf.co/QuixiAI/laserxtral
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,9 +12,8 @@ An experimentation regarding 'lasering' each expert to denoise and enhance model
|
|
| 12 |
|
| 13 |
This model has half size in comparison to the Mixtral 8x7b Instruct. And it basically has the same level of performance (we are working to get a better MMLU score).
|
| 14 |
|
| 15 |
-
Used models (all lasered using laserRMT, except for the base model):
|
| 16 |
|
| 17 |
-
# Laserxtral - 4x7b
|
| 18 |
|
| 19 |
This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
|
| 20 |
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo)
|
|
|
|
| 12 |
|
| 13 |
This model has half size in comparison to the Mixtral 8x7b Instruct. And it basically has the same level of performance (we are working to get a better MMLU score).
|
| 14 |
|
|
|
|
| 15 |
|
| 16 |
+
# Laserxtral - 4x7b (all lasered using laserRMT)
|
| 17 |
|
| 18 |
This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
|
| 19 |
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo)
|