In progress training - batch: 0
Browse files- config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"self_att_type": "sqa",
|
| 13 |
"seq_len": 8192,
|
| 14 |
"skip_memory_cross_attention": true,
|
| 15 |
-
"stm_size":
|
| 16 |
"use_attention_output_bias": false,
|
| 17 |
"use_flash_attention": true,
|
| 18 |
"use_gated": true,
|
|
|
|
| 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,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 64205688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d52752ff18963752efc5d0c829eaba81cc2558dda37bfffb279fc9b9b5dc70c
|
| 3 |
size 64205688
|