Instructions to use fab-an/my_lang-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fab-an/my_lang-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="fab-an/my_lang-model")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("fab-an/my_lang-model") model = AutoModelForCausalLM.from_pretrained("fab-an/my_lang-model") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use fab-an/my_lang-model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "fab-an/my_lang-model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "fab-an/my_lang-model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/fab-an/my_lang-model
- SGLang
How to use fab-an/my_lang-model 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 "fab-an/my_lang-model" \ --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": "fab-an/my_lang-model", "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 "fab-an/my_lang-model" \ --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": "fab-an/my_lang-model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use fab-an/my_lang-model with Docker Model Runner:
docker model run hf.co/fab-an/my_lang-model
metadata
tags:
- generated_from_keras_callback
model-index:
- name: fab-an/my_lang-model
results: []
fab-an/my_lang-model
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 6.5480
- Validation Loss: 6.2459
- Epoch: 2
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 6.9373 | 6.5509 | 0 |
| 6.7565 | 6.4009 | 1 |
| 6.5480 | 6.2459 | 2 |
Framework versions
- Transformers 4.27.1
- TensorFlow 2.11.0
- Datasets 2.10.1
- Tokenizers 0.13.2