Isabelle Cudlitz
commited on
Commit
·
571d599
1
Parent(s):
b07d8c2
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2466,4 +2466,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2466 |
### Framework versions
|
| 2467 |
|
| 2468 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2469 |
- PEFT 0.6.2
|
|
|
|
| 2466 |
### Framework versions
|
| 2467 |
|
| 2468 |
|
| 2469 |
+
- PEFT 0.6.2
|
| 2470 |
+
## Training procedure
|
| 2471 |
+
|
| 2472 |
+
|
| 2473 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2474 |
+
- load_in_8bit: True
|
| 2475 |
+
- load_in_4bit: False
|
| 2476 |
+
- llm_int8_threshold: 6.0
|
| 2477 |
+
- llm_int8_skip_modules: None
|
| 2478 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2479 |
+
- llm_int8_has_fp16_weight: False
|
| 2480 |
+
- bnb_4bit_quant_type: fp4
|
| 2481 |
+
- bnb_4bit_use_double_quant: False
|
| 2482 |
+
- bnb_4bit_compute_dtype: float32
|
| 2483 |
+
|
| 2484 |
+
### Framework versions
|
| 2485 |
+
|
| 2486 |
+
|
| 2487 |
- 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 sha256:7fe4bb69a55e4f395646fee966da75105761043734ac28b6d5c8281fecbee661
|
| 3 |
size 21020682
|