Instructions to use fractalego/fact-checking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fractalego/fact-checking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="fractalego/fact-checking")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("fractalego/fact-checking") model = AutoModelForCausalLM.from_pretrained("fractalego/fact-checking") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use fractalego/fact-checking with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "fractalego/fact-checking" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "fractalego/fact-checking", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/fractalego/fact-checking
- SGLang
How to use fractalego/fact-checking 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 "fractalego/fact-checking" \ --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": "fractalego/fact-checking", "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 "fractalego/fact-checking" \ --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": "fractalego/fact-checking", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use fractalego/fact-checking with Docker Model Runner:
docker model run hf.co/fractalego/fact-checking
Commit ·
856850b
1
Parent(s): a3185c8
Update README.md
Browse files
README.md
CHANGED
|
@@ -37,7 +37,7 @@ print(is_claim_true)
|
|
| 37 |
which gives the output
|
| 38 |
|
| 39 |
```bash
|
| 40 |
-
|
| 41 |
```
|
| 42 |
|
| 43 |
### Probabilistic output with replicas
|
|
@@ -77,7 +77,8 @@ with output
|
|
| 77 |
|
| 78 |
### Score on FEVER
|
| 79 |
|
| 80 |
-
The
|
|
|
|
| 81 |
|
| 82 |
| precision | recall | F1|
|
| 83 |
| --- | --- | --- |
|
|
|
|
| 37 |
which gives the output
|
| 38 |
|
| 39 |
```bash
|
| 40 |
+
False
|
| 41 |
```
|
| 42 |
|
| 43 |
### Probabilistic output with replicas
|
|
|
|
| 77 |
|
| 78 |
### Score on FEVER
|
| 79 |
|
| 80 |
+
The predictions are evaluated on a subset of the FEVER dev dataset,
|
| 81 |
+
restricted to the SUPPORTING and REFUTING options:
|
| 82 |
|
| 83 |
| precision | recall | F1|
|
| 84 |
| --- | --- | --- |
|