Instructions to use ulas742/entropy-0.075 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ulas742/entropy-0.075 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ulas742/entropy-0.075")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ulas742/entropy-0.075") model = AutoModelForCausalLM.from_pretrained("ulas742/entropy-0.075", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ulas742/entropy-0.075 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ulas742/entropy-0.075" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ulas742/entropy-0.075", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ulas742/entropy-0.075
- SGLang
How to use ulas742/entropy-0.075 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 "ulas742/entropy-0.075" \ --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": "ulas742/entropy-0.075", "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 "ulas742/entropy-0.075" \ --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": "ulas742/entropy-0.075", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ulas742/entropy-0.075 with Docker Model Runner:
docker model run hf.co/ulas742/entropy-0.075
|
Download README.md from ulas742/entropy-0.075: direct link, hf CLI and curl.
- Browser
- Download file 1.31 kB
-
https://huggingface.co/ulas742/entropy-0.075/resolve/main/README.md
- Command line
-
hf download hf://ulas742/entropy-0.075/README.md
-
curl -L -o README.md https://huggingface.co/ulas742/entropy-0.075/resolve/main/README.md
1.31 kB
metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
datasets:
- wikimedia/wikipedia
model-index:
- name: checkpoint
results: []
checkpoint
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the wikimedia/wikipedia 20231101.en dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
Framework versions
- Transformers 4.51.3
- Pytorch 2.1.0+cu118
- Datasets 3.2.0
- Tokenizers 0.21.1