Isabelle Cudlitz
commited on
Commit
·
ee0c636
1
Parent(s):
01efb9d
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3132,4 +3132,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3132 |
### Framework versions
|
| 3133 |
|
| 3134 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3135 |
- PEFT 0.6.2
|
|
|
|
| 3132 |
### Framework versions
|
| 3133 |
|
| 3134 |
|
| 3135 |
+
- PEFT 0.6.2
|
| 3136 |
+
## Training procedure
|
| 3137 |
+
|
| 3138 |
+
|
| 3139 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3140 |
+
- load_in_8bit: True
|
| 3141 |
+
- load_in_4bit: False
|
| 3142 |
+
- llm_int8_threshold: 6.0
|
| 3143 |
+
- llm_int8_skip_modules: None
|
| 3144 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3145 |
+
- llm_int8_has_fp16_weight: False
|
| 3146 |
+
- bnb_4bit_quant_type: fp4
|
| 3147 |
+
- bnb_4bit_use_double_quant: False
|
| 3148 |
+
- bnb_4bit_compute_dtype: float32
|
| 3149 |
+
|
| 3150 |
+
### Framework versions
|
| 3151 |
+
|
| 3152 |
+
|
| 3153 |
- 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:b10182d52b9e9680bbebc4b0dfd9166b949185d770697f056616cdd62faee7b5
|
| 3 |
size 21020682
|