Isabelle Cudlitz
commited on
Commit
·
7d018b2
1
Parent(s):
ee0c636
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3150,4 +3150,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3150 |
### Framework versions
|
| 3151 |
|
| 3152 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3153 |
- PEFT 0.6.2
|
|
|
|
| 3150 |
### Framework versions
|
| 3151 |
|
| 3152 |
|
| 3153 |
+
- PEFT 0.6.2
|
| 3154 |
+
## Training procedure
|
| 3155 |
+
|
| 3156 |
+
|
| 3157 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3158 |
+
- load_in_8bit: True
|
| 3159 |
+
- load_in_4bit: False
|
| 3160 |
+
- llm_int8_threshold: 6.0
|
| 3161 |
+
- llm_int8_skip_modules: None
|
| 3162 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3163 |
+
- llm_int8_has_fp16_weight: False
|
| 3164 |
+
- bnb_4bit_quant_type: fp4
|
| 3165 |
+
- bnb_4bit_use_double_quant: False
|
| 3166 |
+
- bnb_4bit_compute_dtype: float32
|
| 3167 |
+
|
| 3168 |
+
### Framework versions
|
| 3169 |
+
|
| 3170 |
+
|
| 3171 |
- 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:cb4bac3b3d9524e39f564a79571ceab7017dd9435bbd3c98da14f90214bac4b5
|
| 3 |
size 21020682
|