commit c91cddb7cb7645aab1672ccdff7089982f78c1c2 Author: ModelHub XC Date: Fri Aug 14 13:47:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: trinhkhng/linear_Merged_Qwen2-0.5B_0.5 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e96d59 --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# Merged_Qwen2-0.5B_0.5 + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge method. + +### Models Merged + +The following models were included in the merge: +* /kaggle/working/debias_Qwen2-0.5B +* /kaggle/working/Qwen2-0.5B + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +dtype: float32 +merge_method: linear +models: +- model: /kaggle/working/Qwen2-0.5B + parameters: + weight: 0.5 +- model: /kaggle/working/debias_Qwen2-0.5B + parameters: + weight: 0.5 +parameters: + normalize: true +tokenizer: + source: /kaggle/working/Qwen2-0.5B + +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..334233f --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,6 @@ +{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system +You are a helpful assistant<|im_end|> +' }}{% endif %}{{'<|im_start|>' + message['role'] + ' +' + message['content'] + '<|im_end|>' + ' +'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..244101b --- /dev/null +++ b/config.json @@ -0,0 +1,57 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 24, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.0.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151646 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..9793319 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,13 @@ +dtype: float32 +merge_method: linear +models: +- model: /kaggle/working/Qwen2-0.5B + parameters: + weight: 0.5 +- model: /kaggle/working/debias_Qwen2-0.5B + parameters: + weight: 0.5 +parameters: + normalize: true +tokenizer: + source: /kaggle/working/Qwen2-0.5B diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..f4831c5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9131981582dd00205fbbcd4e549740c6591e1b788f1ad7e479578244d91f37 +size 1975124112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..408c9fb --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb +size 11418262 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..62fd553 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,18 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "is_local": true, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}