Isabelle Cudlitz
commited on
Commit
·
11ff4e2
1
Parent(s):
6ff7e24
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2502,4 +2502,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2502 |
### Framework versions
|
| 2503 |
|
| 2504 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2505 |
- PEFT 0.6.2
|
|
|
|
| 2502 |
### Framework versions
|
| 2503 |
|
| 2504 |
|
| 2505 |
+
- PEFT 0.6.2
|
| 2506 |
+
## Training procedure
|
| 2507 |
+
|
| 2508 |
+
|
| 2509 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2510 |
+
- load_in_8bit: True
|
| 2511 |
+
- load_in_4bit: False
|
| 2512 |
+
- llm_int8_threshold: 6.0
|
| 2513 |
+
- llm_int8_skip_modules: None
|
| 2514 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2515 |
+
- llm_int8_has_fp16_weight: False
|
| 2516 |
+
- bnb_4bit_quant_type: fp4
|
| 2517 |
+
- bnb_4bit_use_double_quant: False
|
| 2518 |
+
- bnb_4bit_compute_dtype: float32
|
| 2519 |
+
|
| 2520 |
+
### Framework versions
|
| 2521 |
+
|
| 2522 |
+
|
| 2523 |
- 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 sha256:4bf897db7498283a5bbbfe8625a50c61a015f9c1419e066c0cdfccca96b005d9
|
| 3 |
size 21020682
|