Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +10 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- model_hub_mixin
|
| 4 |
+
- pytorch_model_hub_mixin
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 8 |
+
- Code: [More Information Needed]
|
| 9 |
+
- Paper: [More Information Needed]
|
| 10 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_name": "kmfoda/booksum",
|
| 3 |
+
"head_dim": 64,
|
| 4 |
+
"model_name": "meta-llama/Llama-3.2-1B-Instruct",
|
| 5 |
+
"n_sink": 4,
|
| 6 |
+
"num_heads": 32,
|
| 7 |
+
"num_layers": 16,
|
| 8 |
+
"num_samples": 100,
|
| 9 |
+
"sample_seq_len": 1000
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70b299289f19634283dffdcdf7b6d74fa278e7d3ab1f64da335862ce722ceb4b
|
| 3 |
+
size 8519848
|