Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +15 -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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_type": "gqa",
|
| 3 |
+
"dropout": 0.1,
|
| 4 |
+
"hidden_dim": 768,
|
| 5 |
+
"intermediate_dim": 2048,
|
| 6 |
+
"kv_latent_dim": null,
|
| 7 |
+
"max_seq_len": 128,
|
| 8 |
+
"n_head": 12,
|
| 9 |
+
"n_kv_head": 6,
|
| 10 |
+
"n_layer": 12,
|
| 11 |
+
"q_latent_dim": null,
|
| 12 |
+
"rope_base": 10000.0,
|
| 13 |
+
"use_rope": true,
|
| 14 |
+
"vocab_size": 1024
|
| 15 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a3021121a86c3060c7b9a933eef8afc0914fe6c6763438a31298643c4409af3
|
| 3 |
+
size 318001568
|