Upload model trained with Unsloth

#1
by Gurka065 - opened
Files changed (2) hide show
  1. adapter_config.json +11 -6
  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/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit",
5
  "bias": "none",
 
6
  "eva_config": null,
7
  "exclude_modules": null,
8
  "fan_in_fan_out": false,
@@ -19,19 +20,23 @@
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
  "q_proj",
 
27
  "v_proj",
28
- "up_proj",
29
- "k_proj",
30
- "down_proj",
31
- "o_proj",
32
- "gate_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/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit",
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
+ "qalora_group_size": 16,
24
  "r": 16,
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "o_proj",
29
+ "down_proj",
30
+ "k_proj",
31
  "q_proj",
32
+ "gate_proj",
33
  "v_proj",
34
+ "up_proj"
 
 
 
 
35
  ],
36
+ "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
  "use_dora": false,
40
+ "use_qalora": false,
41
  "use_rslora": false
42
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3edbc0c9f4898bf54d6d627bc8589a8ff3f0b93326599216c9475f6432e7d92
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0ff9c7f0252c424e7508e6064a32a8853892751056a7e0884787bf9cbeb7ef
3
+ size 275341720