Peter Ince
commited on
Commit
·
a727fee
1
Parent(s):
b42fce0
update after training finished
Browse files
README.md
CHANGED
|
@@ -28,6 +28,18 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 28 |
- bnb_4bit_use_double_quant: True
|
| 29 |
- bnb_4bit_compute_dtype: bfloat16
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
The following `bitsandbytes` quantization config was used during training:
|
| 32 |
- quant_method: bitsandbytes
|
| 33 |
- load_in_8bit: False
|
|
@@ -41,6 +53,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 41 |
- bnb_4bit_compute_dtype: bfloat16
|
| 42 |
### Framework versions
|
| 43 |
|
|
|
|
| 44 |
- PEFT 0.6.0.dev0
|
| 45 |
- PEFT 0.6.0.dev0
|
| 46 |
|
|
|
|
| 28 |
- bnb_4bit_use_double_quant: True
|
| 29 |
- bnb_4bit_compute_dtype: bfloat16
|
| 30 |
|
| 31 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 32 |
+
- quant_method: bitsandbytes
|
| 33 |
+
- load_in_8bit: False
|
| 34 |
+
- load_in_4bit: True
|
| 35 |
+
- llm_int8_threshold: 6.0
|
| 36 |
+
- llm_int8_skip_modules: None
|
| 37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 38 |
+
- llm_int8_has_fp16_weight: False
|
| 39 |
+
- bnb_4bit_quant_type: nf4
|
| 40 |
+
- bnb_4bit_use_double_quant: True
|
| 41 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 42 |
+
|
| 43 |
The following `bitsandbytes` quantization config was used during training:
|
| 44 |
- quant_method: bitsandbytes
|
| 45 |
- load_in_8bit: False
|
|
|
|
| 53 |
- bnb_4bit_compute_dtype: bfloat16
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
+
- PEFT 0.6.0.dev0
|
| 57 |
- PEFT 0.6.0.dev0
|
| 58 |
- PEFT 0.6.0.dev0
|
| 59 |
|