Isabelle Cudlitz
commited on
Commit
·
0c6656d
1
Parent(s):
2635c53
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3312,4 +3312,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3312 |
### Framework versions
|
| 3313 |
|
| 3314 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3315 |
- PEFT 0.6.2
|
|
|
|
| 3312 |
### Framework versions
|
| 3313 |
|
| 3314 |
|
| 3315 |
+
- PEFT 0.6.2
|
| 3316 |
+
## Training procedure
|
| 3317 |
+
|
| 3318 |
+
|
| 3319 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3320 |
+
- load_in_8bit: True
|
| 3321 |
+
- load_in_4bit: False
|
| 3322 |
+
- llm_int8_threshold: 6.0
|
| 3323 |
+
- llm_int8_skip_modules: None
|
| 3324 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3325 |
+
- llm_int8_has_fp16_weight: False
|
| 3326 |
+
- bnb_4bit_quant_type: fp4
|
| 3327 |
+
- bnb_4bit_use_double_quant: False
|
| 3328 |
+
- bnb_4bit_compute_dtype: float32
|
| 3329 |
+
|
| 3330 |
+
### Framework versions
|
| 3331 |
+
|
| 3332 |
+
|
| 3333 |
- 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 sha256:57edb9c260a600753a0d0acb18c796ecaf8b517e85e8fb5e39529fe358fc0ff2
|
| 3 |
size 21020682
|