Instructions to use thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k") model = AutoModelForCausalLM.from_pretrained("thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k
- SGLang
How to use thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k 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 "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k" \ --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": "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k", "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 "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k" \ --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": "thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k with Docker Model Runner:
docker model run hf.co/thrunlab/sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k
Commit History
-
End of training
Verified signature759985a -
Training in progress, step 1800
Verified signature564ceb7 -
Training in progress, step 1750
Verified signature8a2d5fa -
Training in progress, step 1700
Verified signatureeb2323d -
Training in progress, step 1650
Verified signatureffb4eee -
Training in progress, step 1600
Verified signature11f8a97 -
Training in progress, step 1550
Verified signature81bfbc9 -
Training in progress, step 1500
Verified signature2178618 -
Training in progress, step 1450
Verified signature9d76ebf -
Training in progress, step 1400
Verified signaturecd9c71d -
Training in progress, step 1350
Verified signature49456d7 -
Training in progress, step 1300
Verified signature14219e7 -
Training in progress, step 1250
Verified signature99e0782 -
Training in progress, step 1200
Verified signatured0013c4 -
Training in progress, step 1150
Verified signatureb731f48 -
Training in progress, step 1100
Verified signature5cdd916 -
Training in progress, step 1050
Verified signaturee0bf7ab -
Training in progress, step 1000
Verified signaturecf7793c -
Training in progress, step 950
Verified signaturee3c427c -
Training in progress, step 900
Verified signature943890f -
Training in progress, step 850
Verified signaturebf07547 -
Training in progress, step 800
Verified signature84ec95b -
Training in progress, step 750
Verified signature7749683 -
Training in progress, step 700
Verified signature9c448df -
Training in progress, step 650
Verified signature8c14a38 -
Training in progress, step 600
Verified signaturea88a78c -
Training in progress, step 550
Verified signaturec06c076 -
Training in progress, step 500
Verified signature0a1198d -
Training in progress, step 450
Verified signature178c843 -
Training in progress, step 400
Verified signaturefd51e5a -
Training in progress, step 350
Verified signaturec86faed -
Training in progress, step 300
Verified signature4be2540 -
Training in progress, step 250
Verified signatureffd7ef4 -
Training in progress, step 200
Verified signature8fbebab -
Training in progress, step 150
Verified signature323f631 -
Training in progress, step 100
Verified signature1a4ad5c -
Training in progress, step 50
Verified signaturee5bf1b7 -
Training in progress, step 100
Verified signature76c711c -
Training in progress, step 50
Verified signature08982a9 -
Training in progress, step 1700
Verified signature293f31d -
Training in progress, step 1650
Verified signature0d80db3 -
Training in progress, step 1600
Verified signature08671e0 -
Training in progress, step 1550
Verified signaturee45524c -
Training in progress, step 1500
Verified signature73f6258 -
Training in progress, step 1450
Verified signatured36c2a1 -
Training in progress, step 1400
Verified signature7647ef6 -
Training in progress, step 1350
Verified signature6c1749e -
Training in progress, step 1300
Verified signature41a4e9d -
Training in progress, step 1250
Verified signatureb4c5bfc -
Training in progress, step 1200
Verified signature5c59b9b