Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2610,4 +2610,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2610 |
### Framework versions
|
| 2611 |
|
| 2612 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2613 |
- PEFT 0.6.2
|
|
|
|
| 2610 |
### Framework versions
|
| 2611 |
|
| 2612 |
|
| 2613 |
+
- PEFT 0.6.2
|
| 2614 |
+
## Training procedure
|
| 2615 |
+
|
| 2616 |
+
|
| 2617 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2618 |
+
- load_in_8bit: True
|
| 2619 |
+
- load_in_4bit: False
|
| 2620 |
+
- llm_int8_threshold: 6.0
|
| 2621 |
+
- llm_int8_skip_modules: None
|
| 2622 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2623 |
+
- llm_int8_has_fp16_weight: False
|
| 2624 |
+
- bnb_4bit_quant_type: fp4
|
| 2625 |
+
- bnb_4bit_use_double_quant: False
|
| 2626 |
+
- bnb_4bit_compute_dtype: float32
|
| 2627 |
+
|
| 2628 |
+
### Framework versions
|
| 2629 |
+
|
| 2630 |
+
|
| 2631 |
- 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 sha256:7904a2197e71f48245b5cce1e22b617453635c063b90d13900239e5f25c87a7e
|
| 3 |
size 21020682
|