commit c44133af681a31a58cd8113e3e651656c49f9b94 Author: ModelHub XC Date: Mon May 4 19:17:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: canbingol/gemma3_1B_base-tr-cpt-1epoch_stage4 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..9e476b4 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +library_name: transformers +tags: +- trl +- cpt +datasets: +- canbingol/vngrs-web-corpus-200k +language: +- tr +- en +base_model: +- canbingol/gemma3_1B_base-tr-cpt-1epoch_stage3 +new_version: canbingol/gemma3_1B_base-tr-cpt-2nd_epoch_stage1 +--- + +# Model Card: Gemma3-1B Turkish CPT (150K–200K Subset, 1 Epoch – Stage 4) + +## Overview + +This model is the **Stage 4** Turkish Continued Pretraining (CPT) variant of Gemma-3-1B. + +Unlike Stage 1, which was initialized from `google/gemma-3-1b-pt`, +this model was initialized from: + +- `canbingol/gemma3_1B_base-tr-cpt-1epoch_stage3` + +Stage 4 continues domain adaptation by exposing the model to **new data** rather than repeating the same subset. + +The model was trained for **1 epoch** on samples **150,000 to 200,000** of the Turkish web corpus. + +Importantly, this model is a direct continuation of Stage 3. +Therefore, cumulatively it has been trained on samples **0–200,000** of the corpus (Stage 1: 0–50K, Stage 2: 50K–100K, Stage 3: 100K–150K, Stage 4: 150K–200K). + +This stage corresponds to the **end of the 1-epoch pass over the full 200K-sample dataset** (i.e., completion of the first full epoch via sequential shards). + +--- + +## Training Lineage + +- Stage 0: `google/gemma-3-1b-pt` +- Stage 1: Samples 0–50,000 (1 epoch) +- Stage 2: Samples 50,000–100,000 (1 epoch) +- Stage 3: Samples 100,000–150,000 (1 epoch) +- Stage 4 (this release): Samples 150,000–200,000 (1 epoch, end of epoch-1) + +Cumulative data exposure: **0–200,000 samples** + +This represents **sequential CPT across disjoint data shards**. + +--- + +## Training Setup + +- Dataset: `canbingol/vngrs-web-corpus-200k` +- Subset Used: Samples 150,000–200,000 +- Initialization: Stage 3 checkpoint +- Training Objective: Continued Pretraining +- Epochs: 1 +- Data Regime: Plain text +- Token Count: **~21.6M tokens** +- Cumulative Token Exposure (Stage 1 + Stage 2 + Stage 3 + Stage 4): **~86.1M tokens (approximate)** + +Notes on cumulative exposure: +- Although Stage 4 trains only on the 150K–200K shard, it inherits all adaptations learned from previous stages. +- After this stage, the model has effectively completed exposure to the entire 0–200K dataset range through sequential continuation. + +--- + +## Usage Example + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "canbingol/gemma3_1B_base-tr-cpt-1epoch_stage4" + +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..e3713c2 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7efbbb53e7375cc2a3ae8f85510c7b7b8b45c68603494b06cb313d7786b00663 +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 +}