baichuan2-chat-13b-chinese
Browse files- README.md +2 -2
- adapter_config.json +4 -6
- adapter_model.bin +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: other
|
3 |
-
base_model: baichuan-inc/Baichuan2-13B-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# results
|
15 |
|
16 |
-
This model is a fine-tuned version of [baichuan-inc/Baichuan2-13B-
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
1 |
---
|
2 |
license: other
|
3 |
+
base_model: baichuan-inc/Baichuan2-13B-Chat
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# results
|
15 |
|
16 |
+
This model is a fine-tuned version of [baichuan-inc/Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat) on an unknown dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
adapter_config.json
CHANGED
@@ -1,23 +1,21 @@
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "baichuan-inc/Baichuan2-13B-
|
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":
|
11 |
"lora_dropout": 0.1,
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
-
"r":
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
"W_pack",
|
18 |
-
"
|
19 |
-
"dense_h_to_4h",
|
20 |
-
"dense_4h_to_h"
|
21 |
],
|
22 |
"task_type": "CAUSAL_LM"
|
23 |
}
|
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "baichuan-inc/Baichuan2-13B-Chat",
|
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": 0.1,
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
+
"r": 1,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
"W_pack",
|
18 |
+
"o_proj"
|
|
|
|
|
19 |
],
|
20 |
"task_type": "CAUSAL_LM"
|
21 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3456e260d60c1c9a2186b8bd97a365a9935a87a1953bb67b92e5cddffafe1fb0
|
3 |
+
size 4972557
|
tokenizer_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"add_eos_token": false,
|
4 |
"auto_map": {
|
5 |
"AutoTokenizer": [
|
6 |
-
"baichuan-inc/Baichuan2-13B-
|
7 |
null
|
8 |
]
|
9 |
},
|
|
|
3 |
"add_eos_token": false,
|
4 |
"auto_map": {
|
5 |
"AutoTokenizer": [
|
6 |
+
"baichuan-inc/Baichuan2-13B-Chat--tokenization_baichuan.BaichuanTokenizer",
|
7 |
null
|
8 |
]
|
9 |
},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c5b42a73a5922e9f424220ed93104b7522c3933322acbae24277a9adc13c86
|
3 |
size 4027
|