commit 53d136bea302c977d3d97b42db395b21ae693dd0 Author: ModelHub XC Date: Sun May 31 13:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: canbingol/gemma3_1B_base-tr-cpt-1epoch_stage1 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..378a7a9 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +library_name: transformers +tags: +- trl +- cpt +datasets: +- canbingol/vngrs-web-corpus-200k +language: +- tr +- en +base_model: +- google/gemma-3-1b-pt +new_version: canbingol/gemma3_1B_base-tr-cpt-2nd_epoch_stage1 +--- + +# Model Card: Gemma3-1B Turkish CPT (50K Subset, 1 Epoch – Stage 1) + +## Overview + +This model is a Turkish Continued Pretraining (CPT) variant of `google/gemma-3-1b-pt`. + +The base model was further trained for **1 epoch** on the first **50,000 samples** of a Turkish web corpus. +This stage represents a broader data exposure regime compared to small-subset experiments and aims to improve: + +- Turkish fluency +- Vocabulary coverage +- Domain familiarity +- Statistical adaptation to Turkish web distribution + +This release corresponds to **Stage 1** of a multi-stage CPT pipeline and is intended for research and experimental analysis. + +--- + +## Base Model + +- `google/gemma-3-1b-pt` + +--- + +## Training Setup + +- Dataset: `canbingol/vngrs-web-corpus-200k` +- Subset Used: First 50,000 samples +- Training Objective: Continued Pretraining +- Epochs: 1 +- Data Regime: Plain text +- Token Count (approximate): ~21.5M tokens + +--- + + +## Usage Example + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "canbingol/gemma3_1B_base-tr-cpt-1epoch_stage1" + +device = "cuda" if torch.cuda.is_available() else "cpu" + +model = AutoModelForCausalLM.from_pretrained(model_id) +tokenizer = AutoTokenizer.from_pretrained(model_id) + +model = model.to(device) + +prompt = "bundan böyle" +inputs = tokenizer(prompt, return_tensors="pt").to(device) + +outputs = model.generate( + **inputs, + max_new_tokens=50, + do_sample=True, + temperature=0.8, + top_p=0.9 +) + +generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(generated_text) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..f63e5ac --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 1152, + "initializer_range": 0.02, + "intermediate_size": 6912, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 26, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000, + "rope_type": "default" + } + }, + "sliding_window": 512, + "sliding_window_pattern": 6, + "tie_word_embeddings": true, + "transformers_version": "5.2.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2967bba --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..ed39743 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8245edd43afa7bad7e90a02cef8a676179d011c6f25b8c4fcbf7ef5d9bc2ac40 +size 1999811208 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..899af07 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497 +size 33384443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..af8c9ee --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,23 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "" + }, + "pad_token": "", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}