Isabelle Cudlitz
commited on
Commit
·
607d903
1
Parent(s):
a1dfbaf
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4158,4 +4158,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4158 |
### Framework versions
|
| 4159 |
|
| 4160 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4161 |
- PEFT 0.6.2
|
|
|
|
| 4158 |
### Framework versions
|
| 4159 |
|
| 4160 |
|
| 4161 |
+
- PEFT 0.6.2
|
| 4162 |
+
## Training procedure
|
| 4163 |
+
|
| 4164 |
+
|
| 4165 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4166 |
+
- load_in_8bit: True
|
| 4167 |
+
- load_in_4bit: False
|
| 4168 |
+
- llm_int8_threshold: 6.0
|
| 4169 |
+
- llm_int8_skip_modules: None
|
| 4170 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4171 |
+
- llm_int8_has_fp16_weight: False
|
| 4172 |
+
- bnb_4bit_quant_type: fp4
|
| 4173 |
+
- bnb_4bit_use_double_quant: False
|
| 4174 |
+
- bnb_4bit_compute_dtype: float32
|
| 4175 |
+
|
| 4176 |
+
### Framework versions
|
| 4177 |
+
|
| 4178 |
+
|
| 4179 |
- 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:a95bcd4c8563a102d1d10048629429a8aa75b3c8c4c7f0574f0c33501b335c3f
|
| 3 |
size 21020682
|