Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4518,4 +4518,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4518 |
### Framework versions
|
| 4519 |
|
| 4520 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4521 |
- PEFT 0.6.2
|
|
|
|
| 4518 |
### Framework versions
|
| 4519 |
|
| 4520 |
|
| 4521 |
+
- PEFT 0.6.2
|
| 4522 |
+
## Training procedure
|
| 4523 |
+
|
| 4524 |
+
|
| 4525 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4526 |
+
- load_in_8bit: True
|
| 4527 |
+
- load_in_4bit: False
|
| 4528 |
+
- llm_int8_threshold: 6.0
|
| 4529 |
+
- llm_int8_skip_modules: None
|
| 4530 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4531 |
+
- llm_int8_has_fp16_weight: False
|
| 4532 |
+
- bnb_4bit_quant_type: fp4
|
| 4533 |
+
- bnb_4bit_use_double_quant: False
|
| 4534 |
+
- bnb_4bit_compute_dtype: float32
|
| 4535 |
+
|
| 4536 |
+
### Framework versions
|
| 4537 |
+
|
| 4538 |
+
|
| 4539 |
- 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:a0cbebb0f2de42e0df34e3e78d9b1543d0358a8ac551c9c9959762f7a1e8ff9a
|
| 3 |
size 21020682
|