Upload model
Browse files
README.md
CHANGED
|
@@ -59,6 +59,17 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 59 |
- bnb_4bit_use_double_quant: False
|
| 60 |
- bnb_4bit_compute_dtype: float16
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
The following `bitsandbytes` quantization config was used during training:
|
| 63 |
- load_in_8bit: False
|
| 64 |
- load_in_4bit: True
|
|
@@ -76,5 +87,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 76 |
- PEFT 0.4.0
|
| 77 |
- PEFT 0.4.0
|
| 78 |
- PEFT 0.4.0
|
|
|
|
| 79 |
|
| 80 |
- PEFT 0.4.0
|
|
|
|
| 59 |
- bnb_4bit_use_double_quant: False
|
| 60 |
- bnb_4bit_compute_dtype: float16
|
| 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: False
|
| 71 |
+
- bnb_4bit_compute_dtype: float16
|
| 72 |
+
|
| 73 |
The following `bitsandbytes` quantization config was used during training:
|
| 74 |
- load_in_8bit: False
|
| 75 |
- load_in_4bit: True
|
|
|
|
| 87 |
- PEFT 0.4.0
|
| 88 |
- PEFT 0.4.0
|
| 89 |
- PEFT 0.4.0
|
| 90 |
+
- PEFT 0.4.0
|
| 91 |
|
| 92 |
- PEFT 0.4.0
|