Isabelle Cudlitz
commited on
Commit
·
fe832ec
1
Parent(s):
d3c8e1e
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1278,4 +1278,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1278 |
### Framework versions
|
| 1279 |
|
| 1280 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1281 |
- PEFT 0.6.2
|
|
|
|
| 1278 |
### Framework versions
|
| 1279 |
|
| 1280 |
|
| 1281 |
+
- PEFT 0.6.2
|
| 1282 |
+
## Training procedure
|
| 1283 |
+
|
| 1284 |
+
|
| 1285 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1286 |
+
- load_in_8bit: False
|
| 1287 |
+
- load_in_4bit: True
|
| 1288 |
+
- llm_int8_threshold: 6.0
|
| 1289 |
+
- llm_int8_skip_modules: None
|
| 1290 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1291 |
+
- llm_int8_has_fp16_weight: False
|
| 1292 |
+
- bnb_4bit_quant_type: fp4
|
| 1293 |
+
- bnb_4bit_use_double_quant: True
|
| 1294 |
+
- bnb_4bit_compute_dtype: float32
|
| 1295 |
+
|
| 1296 |
+
### Framework versions
|
| 1297 |
+
|
| 1298 |
+
|
| 1299 |
- 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:c466e6f74a4bc6f089286b47e1702424c480b02ac9a663a752d72cf62ec23e78
|
| 3 |
size 21020682
|