Instructions to use Tele-AI/TeleChat-12B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tele-AI/TeleChat-12B-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Tele-AI/TeleChat-12B-v2", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Tele-AI/TeleChat-12B-v2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tele-AI/TeleChat-12B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tele-AI/TeleChat-12B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tele-AI/TeleChat-12B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tele-AI/TeleChat-12B-v2

SGLang

How to use Tele-AI/TeleChat-12B-v2 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 "Tele-AI/TeleChat-12B-v2" \
    --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": "Tele-AI/TeleChat-12B-v2",
		"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 "Tele-AI/TeleChat-12B-v2" \
        --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": "Tele-AI/TeleChat-12B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tele-AI/TeleChat-12B-v2 with Docker Model Runner:
```
docker model run hf.co/Tele-AI/TeleChat-12B-v2
```

TeleChat-12B-v2

Commit History

Nov 26, 2024

08:36
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
f0453ee

Aug 2, 2024

03:33
Update README.md

shunxing1234

Verified signature
b713215

Jun 18, 2024

01:15
Update generation_config.json

liusx

Verified signature
3d7ef1a
01:15
Update special_tokens_map.json

liusx

Verified signature
ca24ad0

May 20, 2024

08:06
Update README.md

liusx

Verified signature
81bcc8e
06:56
Upload pytorch_model_00004-of-00004.bin

liusx

Verified signature
1b6f3f8
06:19
Upload pytorch_model_00003-of-00004.bin

liusx

Verified signature
ecbd905
05:53
Upload pytorch_model_00002-of-00004.bin

liusx

Verified signature
7f56de0
03:30
Upload pytorch_model_00001-of-00004.bin

liusx

Verified signature
46c4187

May 19, 2024

13:35
upload

liusx14

ab88734

May 17, 2024

15:53
initial commit

liusx

Verified signature
822d7e5

Commit History

Nov 26, 2024

Adding `safetensors` variant of this model⁠

Aug 2, 2024

Update README.md

Jun 18, 2024

Update generation_config.json

Update special_tokens_map.json

May 20, 2024

Update README.md

Upload pytorch_model_00004-of-00004.bin

Upload pytorch_model_00003-of-00004.bin

Upload pytorch_model_00002-of-00004.bin

Upload pytorch_model_00001-of-00004.bin

May 19, 2024

upload

May 17, 2024

initial commit