Instructions to use apthebest01931/rnj-1-instruct-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use apthebest01931/rnj-1-instruct-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir rnj-1-instruct-mlx-4Bit apthebest01931/rnj-1-instruct-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload generation_config.json with huggingface_hub
Browse files- generation_config.json +10 -0
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 128009,
|
| 6 |
+
"pad_token_id": 128001,
|
| 7 |
+
"temperature": 0.2,
|
| 8 |
+
"do_sample": true,
|
| 9 |
+
"transformers_version": "4.51.2"
|
| 10 |
+
}
|