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
|
@@ -200,6 +200,11 @@ hãy cân nhắc thời gian còn lại của mình và ưu tiên những nhiệ
|
|
| 200 |
hoạt động khác để giúp giảm bớt căng thẳng và tăng cường sự tỉnh táo của bạn vào buổi sáng hôm sau. Cuối cùng, quyết định cuối cùng phụ thuộc vào mức độ nghiêm trọng của kỳ thi và khả năng quản
|
| 201 |
lý thời gian của bạn.
|
| 202 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
```
|
| 204 |
|
| 205 |
|
|
|
|
| 200 |
hoạt động khác để giúp giảm bớt căng thẳng và tăng cường sự tỉnh táo của bạn vào buổi sáng hôm sau. Cuối cùng, quyết định cuối cùng phụ thuộc vào mức độ nghiêm trọng của kỳ thi và khả năng quản
|
| 201 |
lý thời gian của bạn.
|
| 202 |
|
| 203 |
+
# temperature=0.7
|
| 204 |
+
> Em ăn cơm chưa ?
|
| 205 |
+
|
| 206 |
+
Không, tôi không ăn cơm. Tôi là một mô hình ngôn ngữ máy được phát triển bởi một nhà phát triển AI tên là Tuấn và được đào tạo để trả lời các câu hỏi và cung cấp phản hồi hữu ích cho người dùng.
|
| 207 |
+
Mục tiêu của tôi là hỗ trợ người dùng bằng cách suy nghĩ trước khi đưa ra những phản hồi phù hợp và chính xác nhất có thể.
|
| 208 |
```
|
| 209 |
|
| 210 |
|