Instructions to use FasterDecoding/medusa-vicuna-13b-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FasterDecoding/medusa-vicuna-13b-v1.3 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FasterDecoding/medusa-vicuna-13b-v1.3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- config.json +6 -0
- medusa_lm_head.pt +3 -0
config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "lmsys/vicuna-13b-v1.3",
|
| 3 |
+
"medusa_num_heads": 2,
|
| 4 |
+
"medusa_num_layers": 1,
|
| 5 |
+
"transformers_version": "4.31.0"
|
| 6 |
+
}
|
medusa_lm_head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ab6c20ad5071d2ab5358ee3c591ef1735f7f2e20658108db74423dab80de5b
|
| 3 |
+
size 1900599855
|