atsuki-yamaguchi
commited on
Commit
•
1d3f4a0
1
Parent(s):
8d25c6e
Upload model
Browse files- README.md +9 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/bloom-7b1-sw-heuristics",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": [
|
13 |
+
"lm_head",
|
14 |
+
"word_embeddings"
|
15 |
+
],
|
16 |
+
"peft_type": "LORA",
|
17 |
+
"r": 8,
|
18 |
+
"revision": null,
|
19 |
+
"target_modules": [
|
20 |
+
"query_key_value",
|
21 |
+
"dense",
|
22 |
+
"dense_h_to_4h",
|
23 |
+
"dense_4h_to_h"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a310b34bbd278d81b69f7292fc6706c09053ff2722b4c781fb64a03b80d984
|
3 |
+
size 1709770296
|