Isabelle Cudlitz
commited on
Commit
·
fe1d304
1
Parent(s):
fe832ec
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1296,4 +1296,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1296 |
### Framework versions
|
| 1297 |
|
| 1298 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1299 |
- PEFT 0.6.2
|
|
|
|
| 1296 |
### Framework versions
|
| 1297 |
|
| 1298 |
|
| 1299 |
+
- PEFT 0.6.2
|
| 1300 |
+
## Training procedure
|
| 1301 |
+
|
| 1302 |
+
|
| 1303 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1304 |
+
- load_in_8bit: False
|
| 1305 |
+
- load_in_4bit: True
|
| 1306 |
+
- llm_int8_threshold: 6.0
|
| 1307 |
+
- llm_int8_skip_modules: None
|
| 1308 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1309 |
+
- llm_int8_has_fp16_weight: False
|
| 1310 |
+
- bnb_4bit_quant_type: fp4
|
| 1311 |
+
- bnb_4bit_use_double_quant: True
|
| 1312 |
+
- bnb_4bit_compute_dtype: float32
|
| 1313 |
+
|
| 1314 |
+
### Framework versions
|
| 1315 |
+
|
| 1316 |
+
|
| 1317 |
- 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:bcdec8cbc18fa56b51960cb147bd597a8ccc31d34720cc84f214a7d5956646df
|
| 3 |
size 21020682
|