Upload model
Browse files- README.md +24 -2
- adapter_config.json +10 -9
- adapter_model.bin +2 -2
README.md
CHANGED
|
@@ -3,8 +3,30 @@ library_name: peft
|
|
| 3 |
---
|
| 4 |
## Training procedure
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
### Framework versions
|
| 7 |
|
| 8 |
-
- PEFT 0.
|
| 9 |
|
| 10 |
-
- PEFT 0.
|
|
|
|
| 3 |
---
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- load_in_8bit: True
|
| 9 |
+
- load_in_4bit: False
|
| 10 |
+
- llm_int8_threshold: 6.0
|
| 11 |
+
- llm_int8_skip_modules: None
|
| 12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
+
- llm_int8_has_fp16_weight: False
|
| 14 |
+
- bnb_4bit_quant_type: fp4
|
| 15 |
+
- bnb_4bit_use_double_quant: False
|
| 16 |
+
- bnb_4bit_compute_dtype: float32
|
| 17 |
+
|
| 18 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 19 |
+
- load_in_8bit: True
|
| 20 |
+
- load_in_4bit: False
|
| 21 |
+
- llm_int8_threshold: 6.0
|
| 22 |
+
- llm_int8_skip_modules: None
|
| 23 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 24 |
+
- llm_int8_has_fp16_weight: False
|
| 25 |
+
- bnb_4bit_quant_type: fp4
|
| 26 |
+
- bnb_4bit_use_double_quant: False
|
| 27 |
+
- bnb_4bit_compute_dtype: float32
|
| 28 |
### Framework versions
|
| 29 |
|
| 30 |
+
- PEFT 0.5.0.dev0
|
| 31 |
|
| 32 |
+
- PEFT 0.5.0.dev0
|
adapter_config.json
CHANGED
|
@@ -1,19 +1,20 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"base_model_name_or_path": "bigscience/bloom-560m",
|
| 3 |
-
"bias": "lora_only",
|
| 4 |
"fan_in_fan_out": false,
|
|
|
|
|
|
|
|
|
|
| 5 |
"inference_mode": true,
|
| 6 |
-
"
|
| 7 |
-
"layers_pattern": null,
|
| 8 |
-
"layers_to_transform": null,
|
| 9 |
-
"lora_alpha": 16,
|
| 10 |
-
"lora_dropout": 0.1,
|
| 11 |
"modules_to_save": null,
|
| 12 |
-
"peft_type": "
|
| 13 |
-
"r": 16,
|
| 14 |
"revision": null,
|
| 15 |
"target_modules": [
|
| 16 |
-
"query_key_value"
|
|
|
|
|
|
|
|
|
|
| 17 |
],
|
| 18 |
"task_type": "TOKEN_CLS"
|
| 19 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
"base_model_name_or_path": "bigscience/bloom-560m",
|
|
|
|
| 4 |
"fan_in_fan_out": false,
|
| 5 |
+
"feedforward_modules": [
|
| 6 |
+
"mlp.dense_4h_to_h"
|
| 7 |
+
],
|
| 8 |
"inference_mode": true,
|
| 9 |
+
"init_ia3_weights": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"modules_to_save": null,
|
| 11 |
+
"peft_type": "IA3",
|
|
|
|
| 12 |
"revision": null,
|
| 13 |
"target_modules": [
|
| 14 |
+
"query_key_value",
|
| 15 |
+
"dense",
|
| 16 |
+
"dense_h_to_4h",
|
| 17 |
+
"dense_4h_to_h"
|
| 18 |
],
|
| 19 |
"task_type": "TOKEN_CLS"
|
| 20 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b9c8ead1cf8e4bf85d5fd85278eb0f84c9929d6d6c1edc11ad89077309b847c
|
| 3 |
+
size 1267543
|