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
|
@@ -140,7 +140,9 @@ This model is a proof of effort that one man can fine-tune his own model to reac
|
|
| 140 |
* Data: https://github.com/vTuanpham/Large_dataset_translator
|
| 141 |
- **Paper:** ...
|
| 142 |
- **Demo:** ...
|
| 143 |
-
|
|
|
|
|
|
|
| 144 |
## Uses
|
| 145 |
|
| 146 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
|
@@ -393,12 +395,8 @@ Nơi những giấc mơ trở thành hiện thực, nơi trái tim tràn ngập
|
|
| 393 |
Nơi tình yêu và hòa bình ngự trị, nơi tình yêu và hòa bình ngự trị.
|
| 394 |
````
|
| 395 |
|
| 396 |
-
|
| 397 |
Note: 120GB of pre-trained Vietnamese data might not be enough for a general question about Vietnamese events.
|
| 398 |
|
| 399 |
-
Here is a kaggle script to quickly test the model:
|
| 400 |
-
* https://www.kaggle.com/code/tuanphamm/t-llama-test
|
| 401 |
-
|
| 402 |
## Training Details
|
| 403 |
|
| 404 |
**Hardware Type:**
|
|
|
|
| 140 |
* Data: https://github.com/vTuanpham/Large_dataset_translator
|
| 141 |
- **Paper:** ...
|
| 142 |
- **Demo:** ...
|
| 143 |
+
- Here is a kaggle script to quickly test the model:
|
| 144 |
+
* https://www.kaggle.com/code/tuanphamm/t-llama-test
|
| 145 |
+
* https://colab.research.google.com/drive/1Y-f0E6C_gN_Iy72UN3-Y_c5RdPgrPai-?usp=sharing
|
| 146 |
## Uses
|
| 147 |
|
| 148 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
|
|
|
| 395 |
Nơi tình yêu và hòa bình ngự trị, nơi tình yêu và hòa bình ngự trị.
|
| 396 |
````
|
| 397 |
|
|
|
|
| 398 |
Note: 120GB of pre-trained Vietnamese data might not be enough for a general question about Vietnamese events.
|
| 399 |
|
|
|
|
|
|
|
|
|
|
| 400 |
## Training Details
|
| 401 |
|
| 402 |
**Hardware Type:**
|