Model save
Browse files- README.md +5 -4
- adapter_config.json +7 -10
- adapter_model.safetensors +1 -1
- tokenizer_config.json +1 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,17 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
library_name: transformers
|
| 4 |
model_name: ebd3853f-27cd-4553-82ef-b572dab7b9c1
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- dpo
|
| 8 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for ebd3853f-27cd-4553-82ef-b572dab7b9c1
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
@@ -27,7 +28,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
|
@@ -36,7 +37,7 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
|
|
| 36 |
|
| 37 |
- TRL: 0.21.0
|
| 38 |
- Transformers: 4.55.0
|
| 39 |
-
- Pytorch: 2.7.
|
| 40 |
- Datasets: 3.6.0
|
| 41 |
- Tokenizers: 0.21.4
|
| 42 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/Qwen2-1.5B-Instruct
|
| 3 |
library_name: transformers
|
| 4 |
model_name: ebd3853f-27cd-4553-82ef-b572dab7b9c1
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- dpo
|
| 8 |
- trl
|
| 9 |
+
- unsloth
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for ebd3853f-27cd-4553-82ef-b572dab7b9c1
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [unsloth/Qwen2-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct).
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
## Quick start
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/buikhacminh1804/sn56-dpo-train/runs/oovhw4uw)
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
|
|
|
| 37 |
|
| 38 |
- TRL: 0.21.0
|
| 39 |
- Transformers: 4.55.0
|
| 40 |
+
- Pytorch: 2.7.0
|
| 41 |
- Datasets: 3.6.0
|
| 42 |
- Tokenizers: 0.21.4
|
| 43 |
|
adapter_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"base_model_class": "Qwen2ForCausalLM",
|
| 5 |
"parent_library": "transformers.models.qwen2.modeling_qwen2"
|
| 6 |
},
|
| 7 |
-
"base_model_name_or_path": "
|
| 8 |
"bias": "none",
|
| 9 |
"corda_config": null,
|
| 10 |
"eva_config": null,
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"loftq_config": {},
|
| 19 |
"lora_alpha": 256,
|
| 20 |
"lora_bias": false,
|
| 21 |
-
"lora_dropout": 0,
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
|
@@ -28,16 +28,13 @@
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
-
"
|
| 32 |
-
"dense_h_to_4h",
|
| 33 |
-
"v_proj",
|
| 34 |
-
"dense_4h_to_h",
|
| 35 |
-
"down_proj",
|
| 36 |
-
"q_proj",
|
| 37 |
"o_proj",
|
| 38 |
-
"
|
|
|
|
| 39 |
"gate_proj",
|
| 40 |
-
"
|
|
|
|
| 41 |
],
|
| 42 |
"target_parameters": null,
|
| 43 |
"task_type": null,
|
|
|
|
| 4 |
"base_model_class": "Qwen2ForCausalLM",
|
| 5 |
"parent_library": "transformers.models.qwen2.modeling_qwen2"
|
| 6 |
},
|
| 7 |
+
"base_model_name_or_path": "unsloth/Qwen2-1.5B-Instruct",
|
| 8 |
"bias": "none",
|
| 9 |
"corda_config": null,
|
| 10 |
"eva_config": null,
|
|
|
|
| 18 |
"loftq_config": {},
|
| 19 |
"lora_alpha": 256,
|
| 20 |
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
|
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
+
"k_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"o_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
"gate_proj",
|
| 36 |
+
"v_proj",
|
| 37 |
+
"up_proj"
|
| 38 |
],
|
| 39 |
"target_parameters": null,
|
| 40 |
"task_type": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 590925768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9deb1cb83df35e07016a8424200366f491487db272574830d75361120230926
|
| 3 |
size 590925768
|
tokenizer_config.json
CHANGED
|
@@ -37,6 +37,7 @@
|
|
| 37 |
"extra_special_tokens": {},
|
| 38 |
"model_max_length": 32768,
|
| 39 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 40 |
"split_special_tokens": false,
|
| 41 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
"unk_token": null
|
|
|
|
| 37 |
"extra_special_tokens": {},
|
| 38 |
"model_max_length": 32768,
|
| 39 |
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "left",
|
| 41 |
"split_special_tokens": false,
|
| 42 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
"unk_token": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6993
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3744309d5bd91cbc003e477210afa9af9f0354355d4a241bce89dc6653e3143
|
| 3 |
size 6993
|