Hugging Face's logo

Heng666
/
falcon-7b-sharded-bf16-english-quote-qlora

PEFT
Model card Files Community
9

Upload model

#8
by ArronStone - opened
base: refs/heads/main
←
from: refs/pr/8
Discussion Files changed
+4
-2
Files changed (3) hide show
  1. README.md +2 -1
  2. adapter_config.json +1 -0
  3. adapter_model.bin +1 -1
README.md CHANGED
@@ -5,6 +5,7 @@ library_name: peft
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
@@ -17,4 +18,4 @@ The following `bitsandbytes` quantization config was used during training:
17
  ### Framework versions
18
 
19
 
20
- - PEFT 0.4.0.dev0
 
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
 
18
  ### Framework versions
19
 
20
 
21
+ - PEFT 0.6.0.dev0
adapter_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
  "bias": "none",
4
  "fan_in_fan_out": false,
 
1
  {
2
+ "auto_mapping": null,
3
  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2edbfdb94380d84d8ad6aa1a7ed48936bf218196eca8dfbe607a05059d7554
3
  size 522284877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f136a356b6850e450bdbc97b9784fb50a28643c7211ff06cf8b004a9786de6
3
  size 522284877