flozi00 commited on
Commit
39d2893
1 Parent(s): 3b6f54f

Upload model

Browse files
Files changed (2) hide show
  1. README.md +26 -0
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -40,6 +40,30 @@ The following `bitsandbytes` quantization config was used during training:
40
  - bnb_4bit_use_double_quant: False
41
  - bnb_4bit_compute_dtype: float16
42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  The following `bitsandbytes` quantization config was used during training:
44
  - quant_method: bitsandbytes
45
  - load_in_8bit: False
@@ -53,6 +77,8 @@ The following `bitsandbytes` quantization config was used during training:
53
  - bnb_4bit_compute_dtype: float16
54
  ### Framework versions
55
 
 
 
56
  - PEFT 0.6.0.dev0
57
  - PEFT 0.6.0.dev0
58
  - PEFT 0.6.0.dev0
 
40
  - bnb_4bit_use_double_quant: False
41
  - bnb_4bit_compute_dtype: float16
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: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float16
54
+
55
+ The following `bitsandbytes` quantization config was used during training:
56
+ - quant_method: bitsandbytes
57
+ - load_in_8bit: False
58
+ - load_in_4bit: True
59
+ - llm_int8_threshold: 6.0
60
+ - llm_int8_skip_modules: None
61
+ - llm_int8_enable_fp32_cpu_offload: False
62
+ - llm_int8_has_fp16_weight: False
63
+ - bnb_4bit_quant_type: fp4
64
+ - bnb_4bit_use_double_quant: False
65
+ - bnb_4bit_compute_dtype: float16
66
+
67
  The following `bitsandbytes` quantization config was used during training:
68
  - quant_method: bitsandbytes
69
  - load_in_8bit: False
 
77
  - bnb_4bit_compute_dtype: float16
78
  ### Framework versions
79
 
80
+ - PEFT 0.6.0.dev0
81
+ - PEFT 0.6.0.dev0
82
  - PEFT 0.6.0.dev0
83
  - PEFT 0.6.0.dev0
84
  - PEFT 0.6.0.dev0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:111e7498401397fcfe678eacbc2ab16e1f749b4033f41d1310e7c46b7f167306
3
  size 1342338829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa7585d757c0218a7e5bb21f480741b465aea5eca67aecbc4cac0e00a56de7b
3
  size 1342338829