Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2538,4 +2538,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2538 |
### Framework versions
|
| 2539 |
|
| 2540 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2541 |
- PEFT 0.6.2
|
|
|
|
| 2538 |
### Framework versions
|
| 2539 |
|
| 2540 |
|
| 2541 |
+
- PEFT 0.6.2
|
| 2542 |
+
## Training procedure
|
| 2543 |
+
|
| 2544 |
+
|
| 2545 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2546 |
+
- load_in_8bit: True
|
| 2547 |
+
- load_in_4bit: False
|
| 2548 |
+
- llm_int8_threshold: 6.0
|
| 2549 |
+
- llm_int8_skip_modules: None
|
| 2550 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2551 |
+
- llm_int8_has_fp16_weight: False
|
| 2552 |
+
- bnb_4bit_quant_type: fp4
|
| 2553 |
+
- bnb_4bit_use_double_quant: False
|
| 2554 |
+
- bnb_4bit_compute_dtype: float32
|
| 2555 |
+
|
| 2556 |
+
### Framework versions
|
| 2557 |
+
|
| 2558 |
+
|
| 2559 |
- 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 sha256:460dca38eb4a1e029f7898e40746392f8e848db5dfe92dd23dd5b7ee2bbe7e07
|
| 3 |
size 21020682
|