t2ance commited on
Commit
26b3515
·
verified ·
1 Parent(s): adb567a
Files changed (2) hide show
  1. adapter_config.json +9 -5
  2. adapter_model.safetensors +1 -1
adapter_config.json CHANGED
@@ -1,9 +1,12 @@
1
  {
 
2
  "alpha_pattern": {},
 
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "Qwen/Qwen3-4B-Thinking-2507",
5
  "bias": "none",
6
  "corda_config": null,
 
7
  "eva_config": null,
8
  "exclude_modules": null,
9
  "fan_in_fan_out": false,
@@ -20,18 +23,19 @@
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
 
23
  "qalora_group_size": 16,
24
  "r": 64,
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "down_proj",
29
- "q_proj",
30
- "k_proj",
31
- "gate_proj",
32
  "o_proj",
 
33
  "up_proj",
34
- "v_proj"
 
 
 
35
  ],
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
 
1
  {
2
+ "alora_invocation_tokens": null,
3
  "alpha_pattern": {},
4
+ "arrow_config": null,
5
  "auto_mapping": null,
6
  "base_model_name_or_path": "Qwen/Qwen3-4B-Thinking-2507",
7
  "bias": "none",
8
  "corda_config": null,
9
+ "ensure_weight_tying": false,
10
  "eva_config": null,
11
  "exclude_modules": null,
12
  "fan_in_fan_out": false,
 
23
  "megatron_core": "megatron.core",
24
  "modules_to_save": null,
25
  "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
  "qalora_group_size": 16,
28
  "r": 64,
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
 
 
 
 
32
  "o_proj",
33
+ "down_proj",
34
  "up_proj",
35
+ "gate_proj",
36
+ "q_proj",
37
+ "v_proj",
38
+ "k_proj"
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c8fac39bbd1319b5eb07f53169930709a8475602b69122e44edddc5e769a7e8
3
  size 528550256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f664a2f87cb16eab69a4e89f59d5248b525c3338914e9bd2f097890cfab4141
3
  size 528550256