Isabelle Cudlitz
commited on
Commit
·
58c6196
1
Parent(s):
7d018b2
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3168,4 +3168,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3168 |
### Framework versions
|
| 3169 |
|
| 3170 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3171 |
- PEFT 0.6.2
|
|
|
|
| 3168 |
### Framework versions
|
| 3169 |
|
| 3170 |
|
| 3171 |
+
- PEFT 0.6.2
|
| 3172 |
+
## Training procedure
|
| 3173 |
+
|
| 3174 |
+
|
| 3175 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3176 |
+
- load_in_8bit: True
|
| 3177 |
+
- load_in_4bit: False
|
| 3178 |
+
- llm_int8_threshold: 6.0
|
| 3179 |
+
- llm_int8_skip_modules: None
|
| 3180 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3181 |
+
- llm_int8_has_fp16_weight: False
|
| 3182 |
+
- bnb_4bit_quant_type: fp4
|
| 3183 |
+
- bnb_4bit_use_double_quant: False
|
| 3184 |
+
- bnb_4bit_compute_dtype: float32
|
| 3185 |
+
|
| 3186 |
+
### Framework versions
|
| 3187 |
+
|
| 3188 |
+
|
| 3189 |
- 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:ae87bd1b454c0db1faf2ed69bb3596231e3e803141c08f601aa5e059408d1020
|
| 3 |
size 21020682
|