Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3060,4 +3060,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3060 |
### Framework versions
|
| 3061 |
|
| 3062 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3063 |
- PEFT 0.6.2
|
|
|
|
| 3060 |
### Framework versions
|
| 3061 |
|
| 3062 |
|
| 3063 |
+
- PEFT 0.6.2
|
| 3064 |
+
## Training procedure
|
| 3065 |
+
|
| 3066 |
+
|
| 3067 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3068 |
+
- load_in_8bit: True
|
| 3069 |
+
- load_in_4bit: False
|
| 3070 |
+
- llm_int8_threshold: 6.0
|
| 3071 |
+
- llm_int8_skip_modules: None
|
| 3072 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3073 |
+
- llm_int8_has_fp16_weight: False
|
| 3074 |
+
- bnb_4bit_quant_type: fp4
|
| 3075 |
+
- bnb_4bit_use_double_quant: False
|
| 3076 |
+
- bnb_4bit_compute_dtype: float32
|
| 3077 |
+
|
| 3078 |
+
### Framework versions
|
| 3079 |
+
|
| 3080 |
+
|
| 3081 |
- 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 sha256:2b57b0705190847affa4be1acbe73b302fe7bd79dc9ccb4dd149f1c1c55f5a5b
|
| 3 |
size 21020682
|