Hugging Face's logo

PNAKTEMPORAL
/
falcon-7b-genscript-v1

PEFT
Model card Files Community
1
PNAKTEMPORAL commited on
Commit
d23aa84
•
1 Parent(s): 94f492f

Upload model

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. adapter_config.json +1 -1
  3. adapter_model.bin +1 -1
README.md CHANGED
@@ -5,26 +5,26 @@ library_name: peft
5
 
6
 
7
  The following `bitsandbytes` quantization config was used during training:
8
- - load_in_8bit: True
9
- - load_in_4bit: False
10
  - llm_int8_threshold: 6.0
11
  - llm_int8_skip_modules: None
12
  - llm_int8_enable_fp32_cpu_offload: False
13
  - llm_int8_has_fp16_weight: False
14
- - bnb_4bit_quant_type: fp4
15
  - bnb_4bit_use_double_quant: False
16
- - bnb_4bit_compute_dtype: float32
17
 
18
  The following `bitsandbytes` quantization config was used during training:
19
- - load_in_8bit: True
20
- - load_in_4bit: False
21
  - llm_int8_threshold: 6.0
22
  - llm_int8_skip_modules: None
23
  - llm_int8_enable_fp32_cpu_offload: False
24
  - llm_int8_has_fp16_weight: False
25
- - bnb_4bit_quant_type: fp4
26
  - bnb_4bit_use_double_quant: False
27
- - bnb_4bit_compute_dtype: float32
28
  ### Framework versions
29
 
30
  - PEFT 0.4.0.dev0
 
5
 
6
 
7
  The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
  - llm_int8_threshold: 6.0
11
  - llm_int8_skip_modules: None
12
  - llm_int8_enable_fp32_cpu_offload: False
13
  - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
  - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
 
18
  The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
  - llm_int8_threshold: 6.0
22
  - llm_int8_skip_modules: None
23
  - llm_int8_enable_fp32_cpu_offload: False
24
  - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
  - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
  ### Framework versions
29
 
30
  - PEFT 0.4.0.dev0
adapter_config.json CHANGED
@@ -7,7 +7,7 @@
7
  "layers_pattern": null,
8
  "layers_to_transform": null,
9
  "lora_alpha": 16,
10
- "lora_dropout": 0.1,
11
  "modules_to_save": null,
12
  "peft_type": "LORA",
13
  "r": 64,
 
7
  "layers_pattern": null,
8
  "layers_to_transform": null,
9
  "lora_alpha": 16,
10
+ "lora_dropout": 0.03,
11
  "modules_to_save": null,
12
  "peft_type": "LORA",
13
  "r": 64,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12cecf81b792c7402ec638ae5e12a7a74156c48b5246cf6985628b1bd13c306c
3
  size 522284877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ceebfbe17b981abc3d8d28799ad0b267bc00583190f86b23d7c730b24f68d0
3
  size 522284877