Isabelle Cudlitz
commited on
Commit
·
c6d4a39
1
Parent(s):
accb046
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1368,4 +1368,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1368 |
### Framework versions
|
| 1369 |
|
| 1370 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1371 |
- PEFT 0.6.2
|
|
|
|
| 1368 |
### Framework versions
|
| 1369 |
|
| 1370 |
|
| 1371 |
+
- PEFT 0.6.2
|
| 1372 |
+
## Training procedure
|
| 1373 |
+
|
| 1374 |
+
|
| 1375 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1376 |
+
- load_in_8bit: True
|
| 1377 |
+
- load_in_4bit: False
|
| 1378 |
+
- llm_int8_threshold: 6.0
|
| 1379 |
+
- llm_int8_skip_modules: None
|
| 1380 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1381 |
+
- llm_int8_has_fp16_weight: False
|
| 1382 |
+
- bnb_4bit_quant_type: fp4
|
| 1383 |
+
- bnb_4bit_use_double_quant: False
|
| 1384 |
+
- bnb_4bit_compute_dtype: float32
|
| 1385 |
+
|
| 1386 |
+
### Framework versions
|
| 1387 |
+
|
| 1388 |
+
|
| 1389 |
- 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 sha256:2cb71361269de6fdcfb09ed38b6169c3f0630364077e68a288c2a4245754c27c
|
| 3 |
size 21020682
|