Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3204,4 +3204,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3204 |
### Framework versions
|
| 3205 |
|
| 3206 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3207 |
- PEFT 0.6.2
|
|
|
|
| 3204 |
### Framework versions
|
| 3205 |
|
| 3206 |
|
| 3207 |
+
- PEFT 0.6.2
|
| 3208 |
+
## Training procedure
|
| 3209 |
+
|
| 3210 |
+
|
| 3211 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3212 |
+
- load_in_8bit: True
|
| 3213 |
+
- load_in_4bit: False
|
| 3214 |
+
- llm_int8_threshold: 6.0
|
| 3215 |
+
- llm_int8_skip_modules: None
|
| 3216 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3217 |
+
- llm_int8_has_fp16_weight: False
|
| 3218 |
+
- bnb_4bit_quant_type: fp4
|
| 3219 |
+
- bnb_4bit_use_double_quant: False
|
| 3220 |
+
- bnb_4bit_compute_dtype: float32
|
| 3221 |
+
|
| 3222 |
+
### Framework versions
|
| 3223 |
+
|
| 3224 |
+
|
| 3225 |
- 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 sha256:9f0923d50f5f56c5be38990f30083d28f5d0dec93cb0de1973db3f8633ab4c84
|
| 3 |
size 21020682
|