Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4482,4 +4482,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4482 |
### Framework versions
|
| 4483 |
|
| 4484 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4485 |
- PEFT 0.6.2
|
|
|
|
| 4482 |
### Framework versions
|
| 4483 |
|
| 4484 |
|
| 4485 |
+
- PEFT 0.6.2
|
| 4486 |
+
## Training procedure
|
| 4487 |
+
|
| 4488 |
+
|
| 4489 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4490 |
+
- load_in_8bit: True
|
| 4491 |
+
- load_in_4bit: False
|
| 4492 |
+
- llm_int8_threshold: 6.0
|
| 4493 |
+
- llm_int8_skip_modules: None
|
| 4494 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4495 |
+
- llm_int8_has_fp16_weight: False
|
| 4496 |
+
- bnb_4bit_quant_type: fp4
|
| 4497 |
+
- bnb_4bit_use_double_quant: False
|
| 4498 |
+
- bnb_4bit_compute_dtype: float32
|
| 4499 |
+
|
| 4500 |
+
### Framework versions
|
| 4501 |
+
|
| 4502 |
+
|
| 4503 |
- 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 sha256:1ca47e611eba79dbaef3c503feb0bebdb032740f2be9e4bfb09d4d02b4fdefbc
|
| 3 |
size 21020682
|