Upload model
Browse files- README.md +19 -0
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -116,4 +116,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 116 |
### Framework versions
|
| 117 |
|
| 118 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
- PEFT 0.6.2
|
|
|
|
| 116 |
### Framework versions
|
| 117 |
|
| 118 |
|
| 119 |
+
- PEFT 0.6.2
|
| 120 |
+
## Training procedure
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 124 |
+
- quant_method: bitsandbytes
|
| 125 |
+
- load_in_8bit: False
|
| 126 |
+
- load_in_4bit: True
|
| 127 |
+
- llm_int8_threshold: 6.0
|
| 128 |
+
- llm_int8_skip_modules: None
|
| 129 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 130 |
+
- llm_int8_has_fp16_weight: False
|
| 131 |
+
- bnb_4bit_quant_type: nf4
|
| 132 |
+
- bnb_4bit_use_double_quant: False
|
| 133 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 134 |
+
|
| 135 |
+
### Framework versions
|
| 136 |
+
|
| 137 |
+
|
| 138 |
- PEFT 0.6.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 75518144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecff9437a7d4a4b4448f3b244c40c9ebd5a35369767176eef07e329e46047c39
|
| 3 |
size 75518144
|