Instructions to use humpf/FireRed-OCR-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use humpf/FireRed-OCR-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir FireRed-OCR-4bit humpf/FireRed-OCR-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload generation_config.json with huggingface_hub
Browse files- generation_config.json +3 -1
generation_config.json
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
-
"eos_token_id":
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 151643,
|
| 6 |
"temperature": 0.7,
|
| 7 |
"top_k": 20,
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645
|
| 6 |
+
],
|
| 7 |
"pad_token_id": 151643,
|
| 8 |
"temperature": 0.7,
|
| 9 |
"top_k": 20,
|