Instructions to use Arc53/docsgpt-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Arc53/docsgpt-14b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Arc53/docsgpt-14b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Arc53/docsgpt-14b") model = AutoModelForCausalLM.from_pretrained("Arc53/docsgpt-14b", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Arc53/docsgpt-14b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Arc53/docsgpt-14b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Arc53/docsgpt-14b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Arc53/docsgpt-14b
- SGLang
How to use Arc53/docsgpt-14b 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 "Arc53/docsgpt-14b" \ --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": "Arc53/docsgpt-14b", "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 "Arc53/docsgpt-14b" \ --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": "Arc53/docsgpt-14b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Arc53/docsgpt-14b with Docker Model Runner:
docker model run hf.co/Arc53/docsgpt-14b
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,7 +62,7 @@ To prepare your prompts make sure you keep this format:
|
|
| 62 |
```
|
| 63 |
|
| 64 |
|
| 65 |
-
Here is an example comparing it to
|
| 66 |
|
| 67 |
Prompt:
|
| 68 |
```
|
|
@@ -206,7 +206,7 @@ docsgpt-14b:
|
|
| 206 |
This is a mock request to the /api/answer endpoint using Python. It sends a JSON in the body with the question and other required parameters. The response is then parsed and returned.
|
| 207 |
```
|
| 208 |
|
| 209 |
-
The original meta-llama/Llama-2-
|
| 210 |
```
|
| 211 |
|
| 212 |
# answer (POST http://127.0.0.1:5000/api/answer)
|
|
|
|
| 62 |
```
|
| 63 |
|
| 64 |
|
| 65 |
+
Here is an example comparing it to meta-llama/Llama-2-14b
|
| 66 |
|
| 67 |
Prompt:
|
| 68 |
```
|
|
|
|
| 206 |
This is a mock request to the /api/answer endpoint using Python. It sends a JSON in the body with the question and other required parameters. The response is then parsed and returned.
|
| 207 |
```
|
| 208 |
|
| 209 |
+
The original meta-llama/Llama-2-14b:
|
| 210 |
```
|
| 211 |
|
| 212 |
# answer (POST http://127.0.0.1:5000/api/answer)
|