Isabelle Cudlitz
commited on
Commit
·
bd4066f
1
Parent(s):
4168eb5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -414,4 +414,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 414 |
### Framework versions
|
| 415 |
|
| 416 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 417 |
- PEFT 0.6.2
|
|
|
|
| 414 |
### Framework versions
|
| 415 |
|
| 416 |
|
| 417 |
+
- PEFT 0.6.2
|
| 418 |
+
## Training procedure
|
| 419 |
+
|
| 420 |
+
|
| 421 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 422 |
+
- load_in_8bit: False
|
| 423 |
+
- load_in_4bit: True
|
| 424 |
+
- llm_int8_threshold: 6.0
|
| 425 |
+
- llm_int8_skip_modules: None
|
| 426 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 427 |
+
- llm_int8_has_fp16_weight: False
|
| 428 |
+
- bnb_4bit_quant_type: fp4
|
| 429 |
+
- bnb_4bit_use_double_quant: True
|
| 430 |
+
- bnb_4bit_compute_dtype: float32
|
| 431 |
+
|
| 432 |
+
### Framework versions
|
| 433 |
+
|
| 434 |
+
|
| 435 |
- 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:bba7bdb74f9a7fc2d377a5d20c0fc798a2ab4b3f030c8e693410c7b8b147e8dc
|
| 3 |
size 21020682
|