Text Generation
Transformers
PyTorch
Safetensors
Vietnamese
English
llama
Eval Results (legacy)
text-generation-inference
Instructions to use capleaf/T-Llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use capleaf/T-Llama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="capleaf/T-Llama")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("capleaf/T-Llama") model = AutoModelForCausalLM.from_pretrained("capleaf/T-Llama") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use capleaf/T-Llama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "capleaf/T-Llama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "capleaf/T-Llama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/capleaf/T-Llama
- SGLang
How to use capleaf/T-Llama 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 "capleaf/T-Llama" \ --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": "capleaf/T-Llama", "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 "capleaf/T-Llama" \ --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": "capleaf/T-Llama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use capleaf/T-Llama with Docker Model Runner:
docker model run hf.co/capleaf/T-Llama
Update README.md
Browse files
README.md
CHANGED
|
@@ -434,9 +434,8 @@ Here is a kaggle script to quickly test the model:
|
|
| 434 |
* Batch size: 2
|
| 435 |
* Gradient accumulation: 128
|
| 436 |
* Effective batch size: 256
|
| 437 |
-
|
| 438 |
-
|
| 439 |
-
- 350k examples of 60% Vietnamese 40% English for 1.4 epoch
|
| 440 |
|
| 441 |
### Training loss
|
| 442 |
|
|
|
|
| 434 |
* Batch size: 2
|
| 435 |
* Gradient accumulation: 128
|
| 436 |
* Effective batch size: 256
|
| 437 |
+
* 250k examples of 70% Vietnamese 30% English for 3.37 epoch
|
| 438 |
+
* 350k examples of 60% Vietnamese 40% English for 1.4 epoch
|
|
|
|
| 439 |
|
| 440 |
### Training loss
|
| 441 |
|