In progress training - batch: 8192
Browse files- config.json +21 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"att_groups": 8,
|
| 3 |
+
"att_heads": 16,
|
| 4 |
+
"att_query_groups": 8,
|
| 5 |
+
"cross_att_type": "sqa",
|
| 6 |
+
"embed_dim": 384,
|
| 7 |
+
"ff_activation": "silu",
|
| 8 |
+
"ff_dim": 1536,
|
| 9 |
+
"ff_dropout": 0.0,
|
| 10 |
+
"num_layers": 15,
|
| 11 |
+
"rope_base": 100000,
|
| 12 |
+
"self_att_type": "sqa",
|
| 13 |
+
"seq_len": 8192,
|
| 14 |
+
"skip_memory_cross_attention": true,
|
| 15 |
+
"stm_size": 1024,
|
| 16 |
+
"use_attention_output_bias": false,
|
| 17 |
+
"use_flash_attention": true,
|
| 18 |
+
"use_gated": true,
|
| 19 |
+
"use_gated_attention": true,
|
| 20 |
+
"vocab_size": 65536
|
| 21 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efc523686cb2ffefbacd9bddff035fc74e4709e1c05a51c94ba5576f805a9d6a
|
| 3 |
+
size 114818464
|