Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4356,4 +4356,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4356 |
### Framework versions
|
| 4357 |
|
| 4358 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4359 |
- PEFT 0.6.2
|
|
|
|
| 4356 |
### Framework versions
|
| 4357 |
|
| 4358 |
|
| 4359 |
+
- PEFT 0.6.2
|
| 4360 |
+
## Training procedure
|
| 4361 |
+
|
| 4362 |
+
|
| 4363 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4364 |
+
- load_in_8bit: True
|
| 4365 |
+
- load_in_4bit: False
|
| 4366 |
+
- llm_int8_threshold: 6.0
|
| 4367 |
+
- llm_int8_skip_modules: None
|
| 4368 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4369 |
+
- llm_int8_has_fp16_weight: False
|
| 4370 |
+
- bnb_4bit_quant_type: fp4
|
| 4371 |
+
- bnb_4bit_use_double_quant: False
|
| 4372 |
+
- bnb_4bit_compute_dtype: float32
|
| 4373 |
+
|
| 4374 |
+
### Framework versions
|
| 4375 |
+
|
| 4376 |
+
|
| 4377 |
- 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 sha256:7d9b0448614677f19cad4a28cb9445a493aaa211f0fd79a3c6609beb30d5a976
|
| 3 |
size 21020682
|