Hugging Face's logo

andrian-kr
/
mistral-7b-ua-gec

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
andrian-kr commited on
Commit
5d19e20
·
verified ·
1 Parent(s): d742f32

Upload model

Browse files
Files changed (2) hide show
  1. adapter_config.json +6 -3
  2. adapter_model.safetensors +2 -2
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,7 +10,7 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 32,
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
@@ -20,8 +20,11 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "q_proj",
24
- "v_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "/kaggle/input/mistral/pytorch/7b-instruct-v0.1-hf/1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
+ "lora_alpha": 16,
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
  "q_proj",
26
+ "o_proj",
27
+ "k_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924e20901924a7cb210358cb28b9b7ac6d5b4d5e72251cf909439580f19badeb
3
- size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee7a79115e4fdf1a35765bc1744b1adf5f787484866d9d50378d3db9a7951eb
3
+ size 23111032