Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3348,4 +3348,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3348 |
### Framework versions
|
| 3349 |
|
| 3350 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3351 |
- PEFT 0.6.2
|
|
|
|
| 3348 |
### Framework versions
|
| 3349 |
|
| 3350 |
|
| 3351 |
+
- PEFT 0.6.2
|
| 3352 |
+
## Training procedure
|
| 3353 |
+
|
| 3354 |
+
|
| 3355 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3356 |
+
- load_in_8bit: True
|
| 3357 |
+
- load_in_4bit: False
|
| 3358 |
+
- llm_int8_threshold: 6.0
|
| 3359 |
+
- llm_int8_skip_modules: None
|
| 3360 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3361 |
+
- llm_int8_has_fp16_weight: False
|
| 3362 |
+
- bnb_4bit_quant_type: fp4
|
| 3363 |
+
- bnb_4bit_use_double_quant: False
|
| 3364 |
+
- bnb_4bit_compute_dtype: float32
|
| 3365 |
+
|
| 3366 |
+
### Framework versions
|
| 3367 |
+
|
| 3368 |
+
|
| 3369 |
- 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:fb6fa7b6c694d5677f0cf1fa6fe0dfb8a964f73ff0108482420164e95baa2ec5
|
| 3 |
size 21020682
|