Instructions to use mingdali/ChatTruth-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mingdali/ChatTruth-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mingdali/ChatTruth-7B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mingdali/ChatTruth-7B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use mingdali/ChatTruth-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mingdali/ChatTruth-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mingdali/ChatTruth-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mingdali/ChatTruth-7B
- SGLang
How to use mingdali/ChatTruth-7B 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 "mingdali/ChatTruth-7B" \ --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": "mingdali/ChatTruth-7B", "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 "mingdali/ChatTruth-7B" \ --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": "mingdali/ChatTruth-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mingdali/ChatTruth-7B with Docker Model Runner:
docker model run hf.co/mingdali/ChatTruth-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,7 @@ language:
|
|
| 24 |
|
| 25 |
```python
|
| 26 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
| 27 |
import torch
|
| 28 |
torch.manual_seed(1234)
|
| 29 |
model_path = 'ChatTruth-7B' # your downloaded model path.
|
|
@@ -33,7 +34,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
| 33 |
# use cuda device
|
| 34 |
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cuda", trust_remote_code=True).eval()
|
| 35 |
|
| 36 |
-
model.generation_config = GenerationConfig.from_pretrained(
|
| 37 |
model.generation_config.top_p = 0.01
|
| 38 |
|
| 39 |
query = tokenizer.from_list_format([
|
|
|
|
| 24 |
|
| 25 |
```python
|
| 26 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 27 |
+
from transformers.generation import GenerationConfig
|
| 28 |
import torch
|
| 29 |
torch.manual_seed(1234)
|
| 30 |
model_path = 'ChatTruth-7B' # your downloaded model path.
|
|
|
|
| 34 |
# use cuda device
|
| 35 |
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cuda", trust_remote_code=True).eval()
|
| 36 |
|
| 37 |
+
model.generation_config = GenerationConfig.from_pretrained(model_path, trust_remote_code=True)
|
| 38 |
model.generation_config.top_p = 0.01
|
| 39 |
|
| 40 |
query = tokenizer.from_list_format([
|