commit b3ec6f99ce88d91d71075166e4ebb6640d882a4d Author: ModelHub XC Date: Sun Apr 12 08:28:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Kashif786/gemma-3-270m-sindhi-SFT 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..b4b8dc5 --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +base_model: Kashif786/gemma-3-270m-sindhi +library_name: transformers +model_name: gemma-3-270m-sindhi-SFT +tags: +- generated_from_trainer +- trl +- sft +licence: license +--- + +# Model Card for gemma-3-270m-sindhi-SFT + +This model is a fine-tuned version of [Kashif786/gemma-3-270m-sindhi](https://huggingface.co/Kashif786/gemma-3-270m-sindhi). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="Kashif786/gemma-3-270m-sindhi-SFT", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with SFT. + +### Framework versions + +- TRL: 1.0.0 +- Transformers: 5.5.0 +- Pytorch: 2.10.0+cu128 +- Datasets: 4.8.3 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8073fff --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "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" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 18, + "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": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "transformers_version": "5.5.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 280212 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..17a525f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..29175f8 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed7bc8fc2b3effc753a07d55803a3e45e17d41a2e4ad40cc447044322ce9452 +size 559350096 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..61c4c17 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a8f2f799318d8aa8dd342edbcf8662b6c57534076688bf5d0d8a3919f650d9 +size 36800791 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 +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..ef4846f --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee73ece9ad9c7653e3f9659f9a6a8c3e781653e04b43c0f14cf6c420c741ffca +size 5713