Upload folder using huggingface_hub
Browse files- README.md +1 -8
- adapter_config.json +3 -10
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,13 +1,6 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
-
pipeline_tag: text-generation
|
| 5 |
-
tags:
|
| 6 |
-
- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
|
| 7 |
-
- lora
|
| 8 |
-
- sft
|
| 9 |
-
- transformers
|
| 10 |
-
- trl
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for Model ID
|
|
@@ -206,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 206 |
[More Information Needed]
|
| 207 |
### Framework versions
|
| 208 |
|
| 209 |
-
- PEFT 0.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
CHANGED
|
@@ -3,9 +3,6 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
-
"corda_config": null,
|
| 7 |
-
"eva_config": null,
|
| 8 |
-
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": true,
|
|
@@ -14,26 +11,22 @@
|
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
"lora_alpha": 75,
|
| 17 |
-
"lora_bias": false,
|
| 18 |
"lora_dropout": 0.45,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
-
"qalora_group_size": 16,
|
| 24 |
"r": 100,
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"o_proj",
|
| 29 |
"gate_proj",
|
| 30 |
-
"qkv_proj",
|
| 31 |
"down_proj",
|
| 32 |
-
"
|
|
|
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
-
"trainable_token_indices": null,
|
| 36 |
"use_dora": false,
|
| 37 |
-
"use_qalora": false,
|
| 38 |
"use_rslora": true
|
| 39 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
| 5 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
|
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
"lora_alpha": 75,
|
|
|
|
| 14 |
"lora_dropout": 0.45,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
|
|
|
| 19 |
"r": 100,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"gate_proj",
|
|
|
|
| 24 |
"down_proj",
|
| 25 |
+
"qkv_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"o_proj"
|
| 28 |
],
|
| 29 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 30 |
"use_dora": false,
|
|
|
|
| 31 |
"use_rslora": true
|
| 32 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 387102128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d7cdd018163395155d5cf7318274d2c06ef6c7670e96a7ad2f472a977d780c2
|
| 3 |
size 387102128
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b827316f258dc7c6db8ce1381b0481f25600a8cf2ad5b9dc6a28d9f11810ca6
|
| 3 |
size 5560
|