checkpoint iter: 2000
Browse files- README.md +9 -0
- config.json +19 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- Library: [More Information Needed]
|
| 9 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "silu",
|
| 3 |
+
"attn_type": "mla",
|
| 4 |
+
"bias": false,
|
| 5 |
+
"d_model": 1024,
|
| 6 |
+
"dropout": 0.2,
|
| 7 |
+
"head_dim": 64,
|
| 8 |
+
"hidden_dim": 1536,
|
| 9 |
+
"kv_lora_rank": 64,
|
| 10 |
+
"mlp": "GLU",
|
| 11 |
+
"num_heads": 46,
|
| 12 |
+
"num_kv_heads": 46,
|
| 13 |
+
"num_layers": 4,
|
| 14 |
+
"q_lora_rank": 192,
|
| 15 |
+
"rope_head_dim": 16,
|
| 16 |
+
"seq_len": 256,
|
| 17 |
+
"vocab_size": 50257,
|
| 18 |
+
"weight_tying": false
|
| 19 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f0b81b4e8bd1a01b4825d2d3dfe324ad7018a19c9aed95ad49aa0c5342ec2a2
|
| 3 |
+
size 554294048
|