Isabelle Cudlitz
commited on
Commit
·
544769e
1
Parent(s):
15ec4da
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1350,4 +1350,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1350 |
### Framework versions
|
| 1351 |
|
| 1352 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1353 |
- PEFT 0.6.2
|
|
|
|
| 1350 |
### Framework versions
|
| 1351 |
|
| 1352 |
|
| 1353 |
+
- PEFT 0.6.2
|
| 1354 |
+
## Training procedure
|
| 1355 |
+
|
| 1356 |
+
|
| 1357 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1358 |
+
- load_in_8bit: False
|
| 1359 |
+
- load_in_4bit: True
|
| 1360 |
+
- llm_int8_threshold: 6.0
|
| 1361 |
+
- llm_int8_skip_modules: None
|
| 1362 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1363 |
+
- llm_int8_has_fp16_weight: False
|
| 1364 |
+
- bnb_4bit_quant_type: fp4
|
| 1365 |
+
- bnb_4bit_use_double_quant: True
|
| 1366 |
+
- bnb_4bit_compute_dtype: float32
|
| 1367 |
+
|
| 1368 |
+
### Framework versions
|
| 1369 |
+
|
| 1370 |
+
|
| 1371 |
- 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 sha256:78ec21bf769947bfb375151847b7cab248f84d827b1b4fac072245c2c5e54170
|
| 3 |
size 21020682
|