jaewoo park
commited on
Commit
·
4ee7dbe
1
Parent(s):
e4c3457
Upload model
Browse files- README.md +5 -5
- adapter_config.json +1 -1
README.md
CHANGED
|
@@ -203,15 +203,15 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 203 |
|
| 204 |
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
- quant_method: bitsandbytes
|
| 206 |
-
- load_in_8bit:
|
| 207 |
-
- load_in_4bit:
|
| 208 |
- llm_int8_threshold: 6.0
|
| 209 |
- llm_int8_skip_modules: None
|
| 210 |
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
- llm_int8_has_fp16_weight: False
|
| 212 |
-
- bnb_4bit_quant_type:
|
| 213 |
-
- bnb_4bit_use_double_quant:
|
| 214 |
-
- bnb_4bit_compute_dtype:
|
| 215 |
|
| 216 |
### Framework versions
|
| 217 |
|
|
|
|
| 203 |
|
| 204 |
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: False
|
| 207 |
+
- load_in_4bit: True
|
| 208 |
- llm_int8_threshold: 6.0
|
| 209 |
- llm_int8_skip_modules: None
|
| 210 |
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: nf4
|
| 213 |
+
- bnb_4bit_use_double_quant: True
|
| 214 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 215 |
|
| 216 |
### Framework versions
|
| 217 |
|
adapter_config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"lora_alpha": 16,
|
| 12 |
-
"lora_dropout": 0.
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
"r": 8,
|
|
|
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
"r": 8,
|