Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4338,4 +4338,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4338 |
### Framework versions
|
| 4339 |
|
| 4340 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4341 |
- PEFT 0.6.2
|
|
|
|
| 4338 |
### Framework versions
|
| 4339 |
|
| 4340 |
|
| 4341 |
+
- PEFT 0.6.2
|
| 4342 |
+
## Training procedure
|
| 4343 |
+
|
| 4344 |
+
|
| 4345 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4346 |
+
- load_in_8bit: True
|
| 4347 |
+
- load_in_4bit: False
|
| 4348 |
+
- llm_int8_threshold: 6.0
|
| 4349 |
+
- llm_int8_skip_modules: None
|
| 4350 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4351 |
+
- llm_int8_has_fp16_weight: False
|
| 4352 |
+
- bnb_4bit_quant_type: fp4
|
| 4353 |
+
- bnb_4bit_use_double_quant: False
|
| 4354 |
+
- bnb_4bit_compute_dtype: float32
|
| 4355 |
+
|
| 4356 |
+
### Framework versions
|
| 4357 |
+
|
| 4358 |
+
|
| 4359 |
- 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 sha256:7bc349f017d7f3df15beb49c379186d2a6ec7b52c750465cad1532267ad22152
|
| 3 |
size 21020682
|