Hugging Face's logo

aymanbakiri
/
MNLP_M3_mcqa_model_adapter

Question Answering
PEFT
Safetensors
mcqa
sft
lora
qwen
unsloth
Generated from Trainer
Model card Files
xet
Community
aymanbakiri commited on
Commit
fe4f81a
路
verified 路
1 Parent(s): d185f8c

Model save

Browse files
Files changed (4) hide show
  1. README.md +3 -3
  2. final_model/adapter_config.json +5 -5
  3. final_model/adapter_model.safetensors +1 -1
  4. final_model/training_args.bin +1 -1
README.md CHANGED
@@ -2,22 +2,22 @@
2
  library_name: peft
3
  base_model: AnnaelleMyriam/SFT_M3_model
4
  tags:
 
5
  - mcqa
6
  - question-answering
7
  - sft
8
  - lora
9
  - qwen
10
- - unsloth
11
  - generated_from_trainer
12
  model-index:
13
- - name: MNLP_M3_mcqa_model_test
14
  results: []
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
  should probably proofread and complete it, then remove this comment. -->
19
 
20
- # MNLP_M3_mcqa_model_test
21
 
22
  This model is a fine-tuned version of [AnnaelleMyriam/SFT_M3_model](https://huggingface.co/AnnaelleMyriam/SFT_M3_model) on an unknown dataset.
23
 
 
2
  library_name: peft
3
  base_model: AnnaelleMyriam/SFT_M3_model
4
  tags:
5
+ - unsloth
6
  - mcqa
7
  - question-answering
8
  - sft
9
  - lora
10
  - qwen
 
11
  - generated_from_trainer
12
  model-index:
13
+ - name: MNLP_M3_mcqa_model_adapter
14
  results: []
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
  should probably proofread and complete it, then remove this comment. -->
19
 
20
+ # MNLP_M3_mcqa_model_adapter
21
 
22
  This model is a fine-tuned version of [AnnaelleMyriam/SFT_M3_model](https://huggingface.co/AnnaelleMyriam/SFT_M3_model) on an unknown dataset.
23
 
final_model/adapter_config.json CHANGED
@@ -24,14 +24,14 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "v_proj",
28
  "o_proj",
29
- "lm_head",
30
  "q_proj",
31
- "k_proj",
32
- "gate_proj",
33
  "up_proj",
34
- "down_proj"
 
 
 
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "gate_proj",
28
  "o_proj",
 
29
  "q_proj",
 
 
30
  "up_proj",
31
+ "lm_head",
32
+ "down_proj",
33
+ "v_proj",
34
+ "k_proj"
35
  ],
36
  "task_type": "CAUSAL_LM",
37
  "trainable_token_indices": null,
final_model/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d84b7e6e62f59ee14e7d4160e7aeb457f515dba8fa18cf678f87a89e5112a4c
3
  size 361377080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d761df02e0abda0ea4847d8797711e00275f6db8b32d3d1dcfd5d18973bee0
3
  size 361377080
final_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a92d59389dc8d4d7ea8af522fd28e7cb89aab94c6027a107713e53cebcdbc6
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fc7fdddb064d87626f246a5a1e81764799aa7ef702d27cd509477470296c1c
3
  size 5777