Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -252,4 +252,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 252 |
### Framework versions
|
| 253 |
|
| 254 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 255 |
- PEFT 0.6.2
|
|
|
|
| 252 |
### Framework versions
|
| 253 |
|
| 254 |
|
| 255 |
+
- PEFT 0.6.2
|
| 256 |
+
## Training procedure
|
| 257 |
+
|
| 258 |
+
|
| 259 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 260 |
+
- load_in_8bit: True
|
| 261 |
+
- load_in_4bit: False
|
| 262 |
+
- llm_int8_threshold: 6.0
|
| 263 |
+
- llm_int8_skip_modules: None
|
| 264 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 265 |
+
- llm_int8_has_fp16_weight: False
|
| 266 |
+
- bnb_4bit_quant_type: fp4
|
| 267 |
+
- bnb_4bit_use_double_quant: False
|
| 268 |
+
- bnb_4bit_compute_dtype: float32
|
| 269 |
+
|
| 270 |
+
### Framework versions
|
| 271 |
+
|
| 272 |
+
|
| 273 |
- 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 sha256:35bf48f9b81f0446aed0e5e1412b04f92148c47c1b9b3d50bbae2713638fdffc
|
| 3 |
size 21020682
|