Isabelle Cudlitz
commited on
Commit
·
b9b0c5e
1
Parent(s):
a8a70fe
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4464,4 +4464,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4464 |
### Framework versions
|
| 4465 |
|
| 4466 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4467 |
- PEFT 0.6.2
|
|
|
|
| 4464 |
### Framework versions
|
| 4465 |
|
| 4466 |
|
| 4467 |
+
- PEFT 0.6.2
|
| 4468 |
+
## Training procedure
|
| 4469 |
+
|
| 4470 |
+
|
| 4471 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4472 |
+
- load_in_8bit: True
|
| 4473 |
+
- load_in_4bit: False
|
| 4474 |
+
- llm_int8_threshold: 6.0
|
| 4475 |
+
- llm_int8_skip_modules: None
|
| 4476 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4477 |
+
- llm_int8_has_fp16_weight: False
|
| 4478 |
+
- bnb_4bit_quant_type: fp4
|
| 4479 |
+
- bnb_4bit_use_double_quant: False
|
| 4480 |
+
- bnb_4bit_compute_dtype: float32
|
| 4481 |
+
|
| 4482 |
+
### Framework versions
|
| 4483 |
+
|
| 4484 |
+
|
| 4485 |
- 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:bb164fee69b437c555e7419bb422a0d89154b706a402ff9c255b87a25e2ff306
|
| 3 |
size 21020682
|