Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4248,4 +4248,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4248 |
### Framework versions
|
| 4249 |
|
| 4250 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4251 |
- PEFT 0.6.2
|
|
|
|
| 4248 |
### Framework versions
|
| 4249 |
|
| 4250 |
|
| 4251 |
+
- PEFT 0.6.2
|
| 4252 |
+
## Training procedure
|
| 4253 |
+
|
| 4254 |
+
|
| 4255 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4256 |
+
- load_in_8bit: True
|
| 4257 |
+
- load_in_4bit: False
|
| 4258 |
+
- llm_int8_threshold: 6.0
|
| 4259 |
+
- llm_int8_skip_modules: None
|
| 4260 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4261 |
+
- llm_int8_has_fp16_weight: False
|
| 4262 |
+
- bnb_4bit_quant_type: fp4
|
| 4263 |
+
- bnb_4bit_use_double_quant: False
|
| 4264 |
+
- bnb_4bit_compute_dtype: float32
|
| 4265 |
+
|
| 4266 |
+
### Framework versions
|
| 4267 |
+
|
| 4268 |
+
|
| 4269 |
- 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 sha256:1dde5fa9df0061f00e74ddd1eed070fdb37f473d7ec19797206f7f6abc38ccf4
|
| 3 |
size 21020682
|