241204
Browse files- adapter_model.safetensors +3 -0
- config.json +4 -37
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e4d9edca8e6c85e295af73e1c608135d99cbe420af8bc614ce7a4342f4dcf05
|
3 |
+
size 27296640
|
config.json
CHANGED
@@ -1,37 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
"base_model_name_or_path": "abacusai/Llama-3-Smaug-8B",
|
6 |
-
"bias": "none",
|
7 |
-
"fan_in_fan_out": false,
|
8 |
-
"inference_mode": true,
|
9 |
-
"init_lora_weights": true,
|
10 |
-
"layer_replication": null,
|
11 |
-
"layers_pattern": null,
|
12 |
-
"layers_to_transform": null,
|
13 |
-
"loftq_config": {},
|
14 |
-
"lora_alpha": 32,
|
15 |
-
"lora_dropout": 0.05,
|
16 |
-
"megatron_config": null,
|
17 |
-
"megatron_core": "megatron.core",
|
18 |
-
"modules_to_save": [
|
19 |
-
"classifier",
|
20 |
-
"score"
|
21 |
-
],
|
22 |
-
"peft_type": "LORA",
|
23 |
-
"r": 16,
|
24 |
-
"rank_pattern": {},
|
25 |
-
"revision": null,
|
26 |
-
"target_modules": [
|
27 |
-
"v_proj",
|
28 |
-
"q_proj"
|
29 |
-
],
|
30 |
-
"task_type": "SEQ_CLS",
|
31 |
-
"use_dora": false,
|
32 |
-
"use_rslora": false,
|
33 |
-
"architectures": [
|
34 |
-
"LlamaForSequenceClassification"
|
35 |
],
|
36 |
"attention_bias": false,
|
37 |
"attention_dropout": 0.0,
|
@@ -54,7 +23,5 @@
|
|
54 |
"torch_dtype": "bfloat16",
|
55 |
"transformers_version": "4.37.2",
|
56 |
"use_cache": true,
|
57 |
-
"vocab_size": 128256
|
58 |
-
|
59 |
-
"problem_type": "regression"
|
60 |
-
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
|
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.37.2",
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 128256
|
27 |
+
}
|
|
|
|