jjeccles commited on
Commit
7008264
·
verified ·
1 Parent(s): 7bec716

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show
  1. adapter_config.json +7 -5
  2. adapter_model.safetensors +2 -2
adapter_config.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "unsloth/Qwen2.5-3B-Instruct",
5
  "bias": "none",
 
6
  "eva_config": null,
7
  "exclude_modules": null,
8
  "fan_in_fan_out": false,
@@ -19,19 +20,20 @@
19
  "megatron_core": "megatron.core",
20
  "modules_to_save": null,
21
  "peft_type": "LORA",
22
- "r": 16,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
  "o_proj",
 
27
  "up_proj",
28
  "v_proj",
29
- "gate_proj",
30
- "q_proj",
31
  "k_proj",
32
- "down_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
 
35
  "use_dora": false,
36
  "use_rslora": false
37
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Qwen3-1.7B",
5
  "bias": "none",
6
+ "corda_config": null,
7
  "eva_config": null,
8
  "exclude_modules": null,
9
  "fan_in_fan_out": false,
 
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
23
+ "r": 4,
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
  "o_proj",
28
+ "q_proj",
29
  "up_proj",
30
  "v_proj",
 
 
31
  "k_proj",
32
+ "down_proj",
33
+ "gate_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
  "use_dora": false,
38
  "use_rslora": false
39
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5793fd2aaf6b8dafa5c1d82ab7d33605434d0e555251d9cdf50f7c161c54804f
3
- size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798224893f2c838b1dd386055aa430a33e800a5f6d2b578072adac21df808f80
3
+ size 17483896