Hugging Face's logo

q1e123
/
peft-starcoder-lora-a100

PEFT
Safetensors
Generated from Trainer
Model card Files Community
q1e123 commited on
Commit
6f61019
•
1 Parent(s): f85870f

Model save

Browse files
Files changed (3) hide show
  1. README.md +2 -2
  2. adapter_config.json +19 -19
  3. training_args.bin +1 -1
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
- base_model: distilgpt2
7
  model-index:
8
  - name: peft-starcoder-lora-a100
9
  results: []
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # peft-starcoder-lora-a100
16
 
17
- This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ base_model: distilbert/distilgpt2
7
  model-index:
8
  - name: peft-starcoder-lora-a100
9
  results: []
 
14
 
15
  # peft-starcoder-lora-a100
16
 
17
+ This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
18
 
19
  ## Model description
20
 
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "distilgpt2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,30 +20,30 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "transformer.h.3.attn.c_proj",
24
- "transformer.h.3.mlp.c_fc",
25
- "transformer.h.5.mlp.c_fc",
26
- "transformer.h.4.mlp.c_fc",
27
- "transformer.h.2.mlp.c_proj",
28
- "transformer.h.0.mlp.c_proj",
29
- "transformer.h.4.attn.c_proj",
30
- "transformer.h.3.mlp.c_proj",
31
  "transformer.h.4.attn.c_attn",
32
- "transformer.h.4.mlp.c_proj",
33
- "transformer.h.3.attn.c_attn",
34
  "transformer.h.1.attn.c_attn",
35
- "transformer.h.0.attn.c_attn",
36
- "transformer.h.1.attn.c_proj",
37
  "transformer.h.1.mlp.c_proj",
38
- "transformer.h.5.mlp.c_proj",
 
 
 
 
 
39
  "transformer.h.2.attn.c_proj",
40
- "transformer.h.5.attn.c_attn",
41
  "transformer.h.0.mlp.c_fc",
42
- "transformer.h.0.attn.c_proj",
43
- "transformer.h.2.mlp.c_fc",
44
  "transformer.h.2.attn.c_attn",
45
- "transformer.h.5.attn.c_proj",
46
- "transformer.h.1.mlp.c_fc"
 
 
 
 
 
 
 
47
  ],
48
  "task_type": "CAUSAL_LM",
49
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "distilbert/distilgpt2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
 
 
 
 
 
23
  "transformer.h.4.attn.c_attn",
24
+ "transformer.h.5.attn.c_attn",
25
+ "transformer.h.4.attn.c_proj",
26
  "transformer.h.1.attn.c_attn",
27
+ "transformer.h.2.mlp.c_proj",
 
28
  "transformer.h.1.mlp.c_proj",
29
+ "transformer.h.4.mlp.c_proj",
30
+ "transformer.h.3.attn.c_proj",
31
+ "transformer.h.4.mlp.c_fc",
32
+ "transformer.h.5.attn.c_proj",
33
+ "transformer.h.0.attn.c_proj",
34
+ "transformer.h.3.attn.c_attn",
35
  "transformer.h.2.attn.c_proj",
 
36
  "transformer.h.0.mlp.c_fc",
 
 
37
  "transformer.h.2.attn.c_attn",
38
+ "transformer.h.0.mlp.c_proj",
39
+ "transformer.h.1.attn.c_proj",
40
+ "transformer.h.5.mlp.c_fc",
41
+ "transformer.h.3.mlp.c_fc",
42
+ "transformer.h.1.mlp.c_fc",
43
+ "transformer.h.3.mlp.c_proj",
44
+ "transformer.h.0.attn.c_attn",
45
+ "transformer.h.5.mlp.c_proj",
46
+ "transformer.h.2.mlp.c_fc"
47
  ],
48
  "task_type": "CAUSAL_LM",
49
  "use_dora": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:905022d7425bfab0d74e1dc861298969f9c63ef170520ac60873a866360e5cff
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5f0f0ada0564f9402e4b8399d0f7dce549cebc056ce5b9a9b91edac79b2585
3
  size 5112