Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -306,4 +306,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 306 |
### Framework versions
|
| 307 |
|
| 308 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 309 |
- PEFT 0.6.2
|
|
|
|
| 306 |
### Framework versions
|
| 307 |
|
| 308 |
|
| 309 |
+
- PEFT 0.6.2
|
| 310 |
+
## Training procedure
|
| 311 |
+
|
| 312 |
+
|
| 313 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 314 |
+
- load_in_8bit: True
|
| 315 |
+
- load_in_4bit: False
|
| 316 |
+
- llm_int8_threshold: 6.0
|
| 317 |
+
- llm_int8_skip_modules: None
|
| 318 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 319 |
+
- llm_int8_has_fp16_weight: False
|
| 320 |
+
- bnb_4bit_quant_type: fp4
|
| 321 |
+
- bnb_4bit_use_double_quant: False
|
| 322 |
+
- bnb_4bit_compute_dtype: float32
|
| 323 |
+
|
| 324 |
+
### Framework versions
|
| 325 |
+
|
| 326 |
+
|
| 327 |
- 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:f6bd231bc8eba2cc4bc08f952779e77130c14997dc4e386a2accc9e7e748d919
|
| 3 |
size 21020682
|