Commit
·
d60234f
1
Parent(s):
bbc6832
End of training
Browse files- README.md +19 -0
- adapter_config.json +1 -1
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -217,4 +217,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 217 |
### Framework versions
|
| 218 |
|
| 219 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
- PEFT 0.6.2
|
|
|
|
| 217 |
### Framework versions
|
| 218 |
|
| 219 |
|
| 220 |
+
- PEFT 0.6.2
|
| 221 |
+
## Training procedure
|
| 222 |
+
|
| 223 |
+
|
| 224 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 225 |
+
- quant_method: bitsandbytes
|
| 226 |
+
- load_in_8bit: False
|
| 227 |
+
- load_in_4bit: True
|
| 228 |
+
- llm_int8_threshold: 6.0
|
| 229 |
+
- llm_int8_skip_modules: None
|
| 230 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 231 |
+
- llm_int8_has_fp16_weight: False
|
| 232 |
+
- bnb_4bit_quant_type: nf4
|
| 233 |
+
- bnb_4bit_use_double_quant: True
|
| 234 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 235 |
+
|
| 236 |
+
### Framework versions
|
| 237 |
+
|
| 238 |
+
|
| 239 |
- PEFT 0.6.2
|
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": 32,
|
|
|
|
| 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": 32,
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67155338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c988ebde6f20272877d93b6165e352f535b9f9b8519dba2497681fb7edefc4a7
|
| 3 |
size 67155338
|