Isabelle Cudlitz
commited on
Commit
·
28b6ea5
1
Parent(s):
55d98a5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -288,4 +288,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 288 |
### Framework versions
|
| 289 |
|
| 290 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 291 |
- PEFT 0.6.2
|
|
|
|
| 288 |
### Framework versions
|
| 289 |
|
| 290 |
|
| 291 |
+
- PEFT 0.6.2
|
| 292 |
+
## Training procedure
|
| 293 |
+
|
| 294 |
+
|
| 295 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 296 |
+
- load_in_8bit: False
|
| 297 |
+
- load_in_4bit: True
|
| 298 |
+
- llm_int8_threshold: 6.0
|
| 299 |
+
- llm_int8_skip_modules: None
|
| 300 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 301 |
+
- llm_int8_has_fp16_weight: False
|
| 302 |
+
- bnb_4bit_quant_type: fp4
|
| 303 |
+
- bnb_4bit_use_double_quant: True
|
| 304 |
+
- bnb_4bit_compute_dtype: float32
|
| 305 |
+
|
| 306 |
+
### Framework versions
|
| 307 |
+
|
| 308 |
+
|
| 309 |
- 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 sha256:41824bef9fd01c13342f03e4cfa437eaa8d746192b12aa33076ad0ed9628cd56
|
| 3 |
size 21020682
|