Isabelle Cudlitz
commited on
Commit
·
4f63de0
1
Parent(s):
58c6196
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3186,4 +3186,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3186 |
### Framework versions
|
| 3187 |
|
| 3188 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3189 |
- PEFT 0.6.2
|
|
|
|
| 3186 |
### Framework versions
|
| 3187 |
|
| 3188 |
|
| 3189 |
+
- PEFT 0.6.2
|
| 3190 |
+
## Training procedure
|
| 3191 |
+
|
| 3192 |
+
|
| 3193 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3194 |
+
- load_in_8bit: True
|
| 3195 |
+
- load_in_4bit: False
|
| 3196 |
+
- llm_int8_threshold: 6.0
|
| 3197 |
+
- llm_int8_skip_modules: None
|
| 3198 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3199 |
+
- llm_int8_has_fp16_weight: False
|
| 3200 |
+
- bnb_4bit_quant_type: fp4
|
| 3201 |
+
- bnb_4bit_use_double_quant: False
|
| 3202 |
+
- bnb_4bit_compute_dtype: float32
|
| 3203 |
+
|
| 3204 |
+
### Framework versions
|
| 3205 |
+
|
| 3206 |
+
|
| 3207 |
- 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 sha256:75a21987ad3983a1faccad8bb6d7c32f836d0042a4fe8f5d1e8583316880edcb
|
| 3 |
size 21020682
|