Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +26 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"args": {
|
| 3 |
+
"compression_mode": "key_val",
|
| 4 |
+
"decompression_mode": "pinverse",
|
| 5 |
+
"device": "cuda",
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"keep_ratio": 0.5,
|
| 8 |
+
"learnable_compression": true,
|
| 9 |
+
"learnable_decompression": true,
|
| 10 |
+
"model_name": "meta-llama/Llama-3.1-8B-instruct",
|
| 11 |
+
"nonlinearity": false,
|
| 12 |
+
"orthonormal_projection_method": "QR",
|
| 13 |
+
"prune_after": 2048,
|
| 14 |
+
"skip_layers": "",
|
| 15 |
+
"training_data_path": "cache/model=Llama-3.1-8B-Instruct_maxchunk=4_chunksize=8192_savestep=512_sampletype=window_keys.pt",
|
| 16 |
+
"verbose": false
|
| 17 |
+
},
|
| 18 |
+
"data_kwargs": {
|
| 19 |
+
"chunk_size": 8192,
|
| 20 |
+
"max_chunks": 4,
|
| 21 |
+
"model_name": "Llama-3.1-8B-Instruct",
|
| 22 |
+
"sample_type": "window",
|
| 23 |
+
"save_dir": "cache",
|
| 24 |
+
"save_every": 512
|
| 25 |
+
}
|
| 26 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c824c43ba65887fdc21bb99d682b95f41e87135b7b2e78a998b0673bc1f3a961
|
| 3 |
+
size 4207072
|