Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3276,4 +3276,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3276 |
### Framework versions
|
| 3277 |
|
| 3278 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3279 |
- PEFT 0.6.2
|
|
|
|
| 3276 |
### Framework versions
|
| 3277 |
|
| 3278 |
|
| 3279 |
+
- PEFT 0.6.2
|
| 3280 |
+
## Training procedure
|
| 3281 |
+
|
| 3282 |
+
|
| 3283 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3284 |
+
- load_in_8bit: True
|
| 3285 |
+
- load_in_4bit: False
|
| 3286 |
+
- llm_int8_threshold: 6.0
|
| 3287 |
+
- llm_int8_skip_modules: None
|
| 3288 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3289 |
+
- llm_int8_has_fp16_weight: False
|
| 3290 |
+
- bnb_4bit_quant_type: fp4
|
| 3291 |
+
- bnb_4bit_use_double_quant: False
|
| 3292 |
+
- bnb_4bit_compute_dtype: float32
|
| 3293 |
+
|
| 3294 |
+
### Framework versions
|
| 3295 |
+
|
| 3296 |
+
|
| 3297 |
- 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 sha256:921034ff74cbfbfa2553b52d4ebc2c2a4959b6326083104369c0b97a8489bbe2
|
| 3 |
size 21020682
|