Isabelle Cudlitz
commited on
Commit
·
d3c8e1e
1
Parent(s):
e526641
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1260,4 +1260,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1260 |
### Framework versions
|
| 1261 |
|
| 1262 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1263 |
- PEFT 0.6.2
|
|
|
|
| 1260 |
### Framework versions
|
| 1261 |
|
| 1262 |
|
| 1263 |
+
- PEFT 0.6.2
|
| 1264 |
+
## Training procedure
|
| 1265 |
+
|
| 1266 |
+
|
| 1267 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1268 |
+
- load_in_8bit: False
|
| 1269 |
+
- load_in_4bit: True
|
| 1270 |
+
- llm_int8_threshold: 6.0
|
| 1271 |
+
- llm_int8_skip_modules: None
|
| 1272 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1273 |
+
- llm_int8_has_fp16_weight: False
|
| 1274 |
+
- bnb_4bit_quant_type: fp4
|
| 1275 |
+
- bnb_4bit_use_double_quant: True
|
| 1276 |
+
- bnb_4bit_compute_dtype: float32
|
| 1277 |
+
|
| 1278 |
+
### Framework versions
|
| 1279 |
+
|
| 1280 |
+
|
| 1281 |
- 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:ee3fe6ac1d428ce4e0385cec829a1e29b6f6c4208fe776b18a3ff2a8466072eb
|
| 3 |
size 21020682
|