Upload model
Browse files
README.md
CHANGED
|
@@ -37,6 +37,17 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 37 |
- bnb_4bit_use_double_quant: False
|
| 38 |
- bnb_4bit_compute_dtype: float16
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
The following `bitsandbytes` quantization config was used during training:
|
| 41 |
- load_in_8bit: False
|
| 42 |
- load_in_4bit: True
|
|
@@ -52,5 +63,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 52 |
- PEFT 0.4.0
|
| 53 |
- PEFT 0.4.0
|
| 54 |
- PEFT 0.4.0
|
|
|
|
| 55 |
|
| 56 |
- PEFT 0.4.0
|
|
|
|
| 37 |
- bnb_4bit_use_double_quant: False
|
| 38 |
- bnb_4bit_compute_dtype: float16
|
| 39 |
|
| 40 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 41 |
+
- load_in_8bit: False
|
| 42 |
+
- load_in_4bit: True
|
| 43 |
+
- llm_int8_threshold: 6.0
|
| 44 |
+
- llm_int8_skip_modules: None
|
| 45 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 46 |
+
- llm_int8_has_fp16_weight: False
|
| 47 |
+
- bnb_4bit_quant_type: nf4
|
| 48 |
+
- bnb_4bit_use_double_quant: False
|
| 49 |
+
- bnb_4bit_compute_dtype: float16
|
| 50 |
+
|
| 51 |
The following `bitsandbytes` quantization config was used during training:
|
| 52 |
- load_in_8bit: False
|
| 53 |
- load_in_4bit: True
|
|
|
|
| 63 |
- PEFT 0.4.0
|
| 64 |
- PEFT 0.4.0
|
| 65 |
- PEFT 0.4.0
|
| 66 |
+
- PEFT 0.4.0
|
| 67 |
|
| 68 |
- PEFT 0.4.0
|