Upload model
Browse files- README.md +19 -0
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -135,4 +135,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 135 |
### Framework versions
|
| 136 |
|
| 137 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
- PEFT 0.6.2
|
|
|
|
| 135 |
### Framework versions
|
| 136 |
|
| 137 |
|
| 138 |
+
- PEFT 0.6.2
|
| 139 |
+
## Training procedure
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 143 |
+
- quant_method: bitsandbytes
|
| 144 |
+
- load_in_8bit: False
|
| 145 |
+
- load_in_4bit: True
|
| 146 |
+
- llm_int8_threshold: 6.0
|
| 147 |
+
- llm_int8_skip_modules: None
|
| 148 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 149 |
+
- llm_int8_has_fp16_weight: False
|
| 150 |
+
- bnb_4bit_quant_type: nf4
|
| 151 |
+
- bnb_4bit_use_double_quant: False
|
| 152 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 153 |
+
|
| 154 |
+
### Framework versions
|
| 155 |
+
|
| 156 |
+
|
| 157 |
- 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:da4fd7cd636c2a8f5cc10cab0a90a70f94a129ab6441c8dbf5cb9ef1a6f289a6
|
| 3 |
size 75518144
|