Hugging Face's logo

lingjoor
/
mistral-7b-Instruct-v0.1-neft-qlora

PEFT
Model card Files Community
natnitaract commited on
Commit
0a599bd
•
1 Parent(s): da71454

Upload 3 files

Browse files
Files changed (3) hide show
  1. README.md +52 -0
  2. adapter_config.json +6 -6
  3. adapter_model.bin +1 -1
README.md CHANGED
@@ -4,6 +4,54 @@ library_name: peft
4
  ## Training procedure
5
 
6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - quant_method: bitsandbytes
9
  - load_in_8bit: False
@@ -29,6 +77,10 @@ The following `bitsandbytes` quantization config was used during training:
29
  - bnb_4bit_compute_dtype: float32
30
  ### Framework versions
31
 
 
 
 
 
32
  - PEFT 0.5.0
33
 
34
  - PEFT 0.5.0
 
4
  ## Training procedure
5
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: False
34
+ - load_in_4bit: True
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: nf4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: False
46
+ - load_in_4bit: True
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: nf4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+
55
  The following `bitsandbytes` quantization config was used during training:
56
  - quant_method: bitsandbytes
57
  - load_in_8bit: False
 
77
  - bnb_4bit_compute_dtype: float32
78
  ### Framework versions
79
 
80
+ - PEFT 0.5.0
81
+ - PEFT 0.5.0
82
+ - PEFT 0.5.0
83
+ - PEFT 0.5.0
84
  - PEFT 0.5.0
85
 
86
  - PEFT 0.5.0
adapter_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "teknium/CollectiveCognition-v1.1-Mistral-7B",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
@@ -14,13 +14,13 @@
14
  "r": 128,
15
  "revision": null,
16
  "target_modules": [
17
- "v_proj",
18
- "o_proj",
19
- "gate_proj",
20
  "k_proj",
21
- "down_proj",
22
  "up_proj",
23
- "q_proj"
 
 
 
 
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
14
  "r": 128,
15
  "revision": null,
16
  "target_modules": [
 
 
 
17
  "k_proj",
 
18
  "up_proj",
19
+ "v_proj",
20
+ "q_proj",
21
+ "down_proj",
22
+ "o_proj",
23
+ "gate_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63fbdefdca4da058e3c5dd1181c180ecb6d98c32ee7c3ef906bf04cba9e254b4
3
  size 1342338829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:115d15d78d7a264b1298653ccdd462ab179e7ebff1a75146204d1a4cfc6fe0ff
3
  size 1342338829