Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3600,4 +3600,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3600 |
### Framework versions
|
| 3601 |
|
| 3602 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3603 |
- PEFT 0.6.2
|
|
|
|
| 3600 |
### Framework versions
|
| 3601 |
|
| 3602 |
|
| 3603 |
+
- PEFT 0.6.2
|
| 3604 |
+
## Training procedure
|
| 3605 |
+
|
| 3606 |
+
|
| 3607 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3608 |
+
- load_in_8bit: True
|
| 3609 |
+
- load_in_4bit: False
|
| 3610 |
+
- llm_int8_threshold: 6.0
|
| 3611 |
+
- llm_int8_skip_modules: None
|
| 3612 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3613 |
+
- llm_int8_has_fp16_weight: False
|
| 3614 |
+
- bnb_4bit_quant_type: fp4
|
| 3615 |
+
- bnb_4bit_use_double_quant: False
|
| 3616 |
+
- bnb_4bit_compute_dtype: float32
|
| 3617 |
+
|
| 3618 |
+
### Framework versions
|
| 3619 |
+
|
| 3620 |
+
|
| 3621 |
- 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:e6bfa54d27a50db7c4087846e18b2a545dd796cba5908fcbe56b3e46a4e8d0fb
|
| 3 |
size 21020682
|