Instructions to use CofeAI/Tele-FLM-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CofeAI/Tele-FLM-1T with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CofeAI/Tele-FLM-1T", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("CofeAI/Tele-FLM-1T", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CofeAI/Tele-FLM-1T with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CofeAI/Tele-FLM-1T" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CofeAI/Tele-FLM-1T", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CofeAI/Tele-FLM-1T
- SGLang
How to use CofeAI/Tele-FLM-1T 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 "CofeAI/Tele-FLM-1T" \ --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": "CofeAI/Tele-FLM-1T", "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 "CofeAI/Tele-FLM-1T" \ --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": "CofeAI/Tele-FLM-1T", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CofeAI/Tele-FLM-1T with Docker Model Runner:
docker model run hf.co/CofeAI/Tele-FLM-1T
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,6 +65,9 @@ The parallel training setup for Tele-FLM-1T is configured as follows: tensor par
|
|
| 65 |
|
| 66 |
[FLM-101B](https://huggingface.co/CofeAI/FLM-101B)
|
| 67 |
|
|
|
|
|
|
|
|
|
|
| 68 |
## Citation
|
| 69 |
If you find our work helpful, please consider citing it.
|
| 70 |
```
|
|
|
|
| 65 |
|
| 66 |
[FLM-101B](https://huggingface.co/CofeAI/FLM-101B)
|
| 67 |
|
| 68 |
+
## Acknowledgements
|
| 69 |
+
This work was supported by the National Science and Technology Major Project (No. 2022ZD0116314).
|
| 70 |
+
|
| 71 |
## Citation
|
| 72 |
If you find our work helpful, please consider citing it.
|
| 73 |
```
|