enmingzhangzz commited on
Commit
7c7c908
·
verified ·
1 Parent(s): 6474444

Publish scopd-plus-reverse-kl

Browse files
models/scopd-plus-reverse-kl/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ # SCOPD+ Reverse KL
2
+
3
+ LoRA adapter for Qwen2.5-VL-7B-Instruct.
4
+
5
+ Objective: reverse KL: KL(student || teacher).
6
+
7
+ Selection: top 10% budget-JSD response tokens.
8
+
9
+ See the [collection model card](../../README.md) for download and evaluation.
models/scopd-plus-reverse-kl/adapter_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": "layers",
14
+ "layers_to_transform": [
15
+ 0,
16
+ 1,
17
+ 2,
18
+ 3,
19
+ 4,
20
+ 5,
21
+ 6,
22
+ 7,
23
+ 8,
24
+ 9,
25
+ 10,
26
+ 11,
27
+ 12,
28
+ 13,
29
+ 14,
30
+ 15,
31
+ 16,
32
+ 17,
33
+ 18,
34
+ 19,
35
+ 20,
36
+ 21,
37
+ 22,
38
+ 23,
39
+ 24,
40
+ 25,
41
+ 26,
42
+ 27
43
+ ],
44
+ "loftq_config": {},
45
+ "lora_alpha": 32,
46
+ "lora_bias": false,
47
+ "lora_dropout": 0.0,
48
+ "megatron_config": null,
49
+ "megatron_core": "megatron.core",
50
+ "modules_to_save": null,
51
+ "peft_type": "LORA",
52
+ "qalora_group_size": 16,
53
+ "r": 16,
54
+ "rank_pattern": {},
55
+ "revision": "cc594898137f460bfe9f0759e9844b3ce807cfb5",
56
+ "target_modules": [
57
+ "v_proj",
58
+ "up_proj",
59
+ "o_proj",
60
+ "down_proj",
61
+ "gate_proj",
62
+ "k_proj",
63
+ "q_proj"
64
+ ],
65
+ "target_parameters": null,
66
+ "task_type": "CAUSAL_LM",
67
+ "trainable_token_indices": null,
68
+ "use_dora": false,
69
+ "use_qalora": false,
70
+ "use_rslora": false
71
+ }
models/scopd-plus-reverse-kl/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7c4004928c80f85a66d216c6d17b17005fe89740da946d7597225775b00baa
3
+ size 161539072
models/scopd-plus-reverse-kl/provenance.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "id": "scopd-plus-reverse-kl",
3
+ "label": "SCOPD+ Reverse KL",
4
+ "objective": "reverse KL: KL(student || teacher)",
5
+ "selection": "top 10% budget-JSD response tokens",
6
+ "selection_fraction": 0.1,
7
+ "budget_delta": 0.01,
8
+ "adapter_sha256": "1a7c4004928c80f85a66d216c6d17b17005fe89740da946d7597225775b00baa",
9
+ "source_revision": "dc2490eaf9b8b35b7e5553080dd985d0ab6a86a3",
10
+ "base_model": "Qwen/Qwen2.5-VL-7B-Instruct",
11
+ "base_revision": "cc594898137f460bfe9f0759e9844b3ce807cfb5",
12
+ "merged": false,
13
+ "format": "peft_lora",
14
+ "dtype": "float32",
15
+ "inference_dtype": "bfloat16",
16
+ "questions_processed": 10240,
17
+ "path": "models/scopd-plus-reverse-kl",
18
+ "tensor_count": 392,
19
+ "parameter_count": 40370176,
20
+ "weight_bytes": 161480704,
21
+ "lora_rank": 16,
22
+ "lora_alpha": 32,
23
+ "lora_dropout": 0.0
24
+ }