Isabelle Cudlitz
commited on
Commit
·
6ff7e24
1
Parent(s):
571d599
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2484,4 +2484,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2484 |
### Framework versions
|
| 2485 |
|
| 2486 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2487 |
- PEFT 0.6.2
|
|
|
|
| 2484 |
### Framework versions
|
| 2485 |
|
| 2486 |
|
| 2487 |
+
- PEFT 0.6.2
|
| 2488 |
+
## Training procedure
|
| 2489 |
+
|
| 2490 |
+
|
| 2491 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2492 |
+
- load_in_8bit: True
|
| 2493 |
+
- load_in_4bit: False
|
| 2494 |
+
- llm_int8_threshold: 6.0
|
| 2495 |
+
- llm_int8_skip_modules: None
|
| 2496 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2497 |
+
- llm_int8_has_fp16_weight: False
|
| 2498 |
+
- bnb_4bit_quant_type: fp4
|
| 2499 |
+
- bnb_4bit_use_double_quant: False
|
| 2500 |
+
- bnb_4bit_compute_dtype: float32
|
| 2501 |
+
|
| 2502 |
+
### Framework versions
|
| 2503 |
+
|
| 2504 |
+
|
| 2505 |
- 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 sha256:0a6f48113ca4dc771d267fd9b0b2e024e94d7746d0c17eb33affab4bf32da505
|
| 3 |
size 21020682
|