Instructions to use waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2") model = AutoModelForCausalLM.from_pretrained("waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2
- SGLang
How to use waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-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 "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-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": "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-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 "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-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": "waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2 with Docker Model Runner:
docker model run hf.co/waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2
quant of Mihaiii's Pallas-0.5-LASER-0.6
python3 convert.py \
-i /input/Mihaiii_Pallas-0.5-LASER-0.6/ \
-c /input/pippa_cleaned/0000.parquet \
-o /output/temp/ \
-cf /output/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2/ \
-l 8192 \
-ml 8192 \
-b 4.65 \
-hb 6
- Downloads last month
- 1
Model tree for waldie/Pallas-0.5-LASER-0.6-4.65bpw-h6-exl2
Base model
Mihaiii/Pallas-0.5 Finetuned
Mihaiii/Pallas-0.5-LASER-0.1 Finetuned
Mihaiii/Pallas-0.5-LASER-0.2 Finetuned
Mihaiii/Pallas-0.5-LASER-0.3 Finetuned
Mihaiii/Pallas-0.5-LASER-0.4 Finetuned
Mihaiii/Pallas-0.5-LASER-0.5