Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4122,4 +4122,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4122 |
### Framework versions
|
| 4123 |
|
| 4124 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4125 |
- PEFT 0.6.2
|
|
|
|
| 4122 |
### Framework versions
|
| 4123 |
|
| 4124 |
|
| 4125 |
+
- PEFT 0.6.2
|
| 4126 |
+
## Training procedure
|
| 4127 |
+
|
| 4128 |
+
|
| 4129 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4130 |
+
- load_in_8bit: True
|
| 4131 |
+
- load_in_4bit: False
|
| 4132 |
+
- llm_int8_threshold: 6.0
|
| 4133 |
+
- llm_int8_skip_modules: None
|
| 4134 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4135 |
+
- llm_int8_has_fp16_weight: False
|
| 4136 |
+
- bnb_4bit_quant_type: fp4
|
| 4137 |
+
- bnb_4bit_use_double_quant: False
|
| 4138 |
+
- bnb_4bit_compute_dtype: float32
|
| 4139 |
+
|
| 4140 |
+
### Framework versions
|
| 4141 |
+
|
| 4142 |
+
|
| 4143 |
- PEFT 0.6.2
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21020682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:504e5b40634c3c3f9ddb57d7192a29511ed4f2d3d6bbbdff97d9c2e97070f137
|
| 3 |
size 21020682
|