abdullah commited on
Commit
6c0b56b
1 Parent(s): 8c512f9

Training in progress epoch 1

Browse files
Files changed (2) hide show
  1. README.md +12 -0
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -26,6 +26,17 @@ The following `bitsandbytes` quantization config was used during training:
26
  - bnb_4bit_use_double_quant: False
27
  - bnb_4bit_compute_dtype: float32
28
 
 
 
 
 
 
 
 
 
 
 
 
29
  The following `bitsandbytes` quantization config was used during training:
30
  - load_in_8bit: True
31
  - load_in_4bit: False
@@ -38,6 +49,7 @@ The following `bitsandbytes` quantization config was used during training:
38
  - bnb_4bit_compute_dtype: float32
39
  ### Framework versions
40
 
 
41
  - PEFT 0.5.0.dev0
42
  - PEFT 0.5.0.dev0
43
 
 
26
  - bnb_4bit_use_double_quant: False
27
  - bnb_4bit_compute_dtype: float32
28
 
29
+ The following `bitsandbytes` quantization config was used during training:
30
+ - load_in_8bit: True
31
+ - load_in_4bit: False
32
+ - llm_int8_threshold: 6.0
33
+ - llm_int8_skip_modules: None
34
+ - llm_int8_enable_fp32_cpu_offload: False
35
+ - llm_int8_has_fp16_weight: False
36
+ - bnb_4bit_quant_type: fp4
37
+ - bnb_4bit_use_double_quant: False
38
+ - bnb_4bit_compute_dtype: float32
39
+
40
  The following `bitsandbytes` quantization config was used during training:
41
  - load_in_8bit: True
42
  - load_in_4bit: False
 
49
  - bnb_4bit_compute_dtype: float32
50
  ### Framework versions
51
 
52
+ - PEFT 0.5.0.dev0
53
  - PEFT 0.5.0.dev0
54
  - PEFT 0.5.0.dev0
55
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c023d17e37560964a10c2f045f91995bbd144c8c0ac67dc60d3ed00c9d8b9248
3
  size 3591693
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ef30857972a99960609013d7f770fafab05316ad1f998a44d0cad4d25dd49f
3
  size 3591693