Instructions to use Narsil/mistral-medusa2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Narsil/mistral-medusa2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Narsil/mistral-medusa2", device_map="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": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 3 |
+
"medusa_num_heads": 3,
|
| 4 |
+
"medusa_num_layers": 1,
|
| 5 |
+
"transformers_version": "4.37.1"
|
| 6 |
+
}
|
medusa_lm_head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:357fbc96163cab5306da09430ae36e16dec463f989695bd1e4f5a5f2067c1a4b
|
| 3 |
+
size 887123735
|