checkpoint iter: 19999
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 |
+
"attention_type": "k_is_v",
|
4 |
+
"attn_type": "mla",
|
5 |
+
"bias": false,
|
6 |
+
"d_model": 1024,
|
7 |
+
"dropout": 0.2,
|
8 |
+
"head_dim": 64,
|
9 |
+
"hidden_dim": 1536,
|
10 |
+
"kv_lora_rank": null,
|
11 |
+
"mlp": "glu",
|
12 |
+
"num_heads": 21,
|
13 |
+
"num_kv_heads": 0,
|
14 |
+
"num_layers": 16,
|
15 |
+
"rope_head_dim": 64,
|
16 |
+
"seq_len": 256,
|
17 |
+
"vocab_size": 50257,
|
18 |
+
"weight_tying": true
|
19 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ce825579c3b366726c8ca4a3a96b8916bc4d08c97ba243b1c09d9701543080c
|
3 |
+
size 772363656
|