Phoenixsymbol
commited on
Commit
·
8d4c047
1
Parent(s):
a06aa1b
Upload model
Browse files
README.md
CHANGED
@@ -59,6 +59,28 @@ The following `bitsandbytes` quantization config was used during training:
|
|
59 |
- bnb_4bit_use_double_quant: True
|
60 |
- bnb_4bit_compute_dtype: bfloat16
|
61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
The following `bitsandbytes` quantization config was used during training:
|
63 |
- load_in_8bit: False
|
64 |
- load_in_4bit: True
|
@@ -76,5 +98,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
76 |
- PEFT 0.5.0.dev0
|
77 |
- PEFT 0.5.0.dev0
|
78 |
- PEFT 0.5.0.dev0
|
|
|
|
|
79 |
|
80 |
- PEFT 0.5.0.dev0
|
|
|
59 |
- bnb_4bit_use_double_quant: True
|
60 |
- bnb_4bit_compute_dtype: bfloat16
|
61 |
|
62 |
+
The following `bitsandbytes` quantization config was used during training:
|
63 |
+
- load_in_8bit: False
|
64 |
+
- load_in_4bit: True
|
65 |
+
- llm_int8_threshold: 6.0
|
66 |
+
- llm_int8_skip_modules: None
|
67 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
68 |
+
- llm_int8_has_fp16_weight: False
|
69 |
+
- bnb_4bit_quant_type: nf4
|
70 |
+
- bnb_4bit_use_double_quant: True
|
71 |
+
- bnb_4bit_compute_dtype: bfloat16
|
72 |
+
|
73 |
+
The following `bitsandbytes` quantization config was used during training:
|
74 |
+
- load_in_8bit: False
|
75 |
+
- load_in_4bit: True
|
76 |
+
- llm_int8_threshold: 6.0
|
77 |
+
- llm_int8_skip_modules: None
|
78 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
79 |
+
- llm_int8_has_fp16_weight: False
|
80 |
+
- bnb_4bit_quant_type: nf4
|
81 |
+
- bnb_4bit_use_double_quant: True
|
82 |
+
- bnb_4bit_compute_dtype: bfloat16
|
83 |
+
|
84 |
The following `bitsandbytes` quantization config was used during training:
|
85 |
- load_in_8bit: False
|
86 |
- load_in_4bit: True
|
|
|
98 |
- PEFT 0.5.0.dev0
|
99 |
- PEFT 0.5.0.dev0
|
100 |
- PEFT 0.5.0.dev0
|
101 |
+
- PEFT 0.5.0.dev0
|
102 |
+
- PEFT 0.5.0.dev0
|
103 |
|
104 |
- PEFT 0.5.0.dev0
|