Isabelle Cudlitz
commited on
Commit
·
2917d04
1
Parent(s):
ba75fc6
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4428,4 +4428,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4428 |
### Framework versions
|
| 4429 |
|
| 4430 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4431 |
- PEFT 0.6.2
|
|
|
|
| 4428 |
### Framework versions
|
| 4429 |
|
| 4430 |
|
| 4431 |
+
- PEFT 0.6.2
|
| 4432 |
+
## Training procedure
|
| 4433 |
+
|
| 4434 |
+
|
| 4435 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4436 |
+
- load_in_8bit: True
|
| 4437 |
+
- load_in_4bit: False
|
| 4438 |
+
- llm_int8_threshold: 6.0
|
| 4439 |
+
- llm_int8_skip_modules: None
|
| 4440 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4441 |
+
- llm_int8_has_fp16_weight: False
|
| 4442 |
+
- bnb_4bit_quant_type: fp4
|
| 4443 |
+
- bnb_4bit_use_double_quant: False
|
| 4444 |
+
- bnb_4bit_compute_dtype: float32
|
| 4445 |
+
|
| 4446 |
+
### Framework versions
|
| 4447 |
+
|
| 4448 |
+
|
| 4449 |
- 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 sha256:25503a75ccd35a834cf170257f7257fdf87118680198eb440cdf6f68735c4ac2
|
| 3 |
size 21020682
|