commit 3beddb65f6618972b49ecb2057624e2e3b75f97e Author: ModelHub XC Date: Fri Jun 5 03:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: 24-mohamedyehia/Gloss2Text-V1-Gemma3-270M 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/Modelfile b/Modelfile new file mode 100644 index 0000000..84239cf --- /dev/null +++ b/Modelfile @@ -0,0 +1,14 @@ +# ollama modelfile auto-generated by llamafactory + +FROM . + +TEMPLATE """{{ if .System }}{{ .System }} + +{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}user +{{ .Content }} +model +{{ else if eq .Role "assistant" }}{{ .Content }} +{{ end }}{{ end }}""" + +PARAMETER stop "" +PARAMETER num_ctx 4096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..40e0170 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +license: apache-2.0 +datasets: +- 24-mohamedyehia/gloss2text-Ar-sft +language: +- ar +base_model: +- google/gemma-3-270m-it +pipeline_tag: text-generation +tags: +- sign-language +- arabic +- ArSL +- gloss-to-text +- gemma-3 +- accessibility +--- + +# Gloss2Text-V1-Gemma3-270M (Merged) + +## Overview +**Gloss2Text-V1-Gemma3-270M** is a fine-tuned version of Google's **Gemma-3-270m-it**, optimized for **Arabic Sign Language (ArSL) gloss-to-text translation**. + +This release is **merged**, which means the LoRA adapters have already been fused into the base model weights for faster inference and easier plug-and-play usage. + +## Model Description +- **Task:** Converts a sequence of Arabic glosses into a natural, grammatically correct Modern Standard Arabic (MSA) sentence. +- **Input format:** Arabic gloss text, for example: "أنا شرب ماء الآن" +- **Output format:** Clean MSA text, for example: "أنا أشرب الماء الآن." +- **Architecture:** Gemma-3, 270M parameters +- **Training method:** Supervised fine-tuning with LoRA (rank 64), then merged + +## Training Highlights +The model was trained on a specialized dataset containing diverse ArSL gloss-sentence pairs. +- **Final eval loss:** ~0.34 +- **Precision:** Trained with `bf16` for improved numerical stability + + +## How to Use +Because this is a merged model, you can load it directly with the `transformers` library without needing `peft`: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "24-mohamedyehia/Gloss2Text-V1-Gemma3-270M" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", +) + +def translate_gloss(gloss_text): + prompt = f"Translate ArSL gloss to an MSA sentence.\nGloss: {gloss_text}\nOutput: " + inputs = tokenizer(prompt, return_tensors="pt").to("cuda") + outputs = model.generate(**inputs, max_new_tokens=50) + return tokenizer.decode(outputs[0], skip_special_tokens=True) + + +# Example +print(translate_gloss("أنا ذهاب صيدلية")) +``` + + +## Developer + +Developed by **Mohamed Yehia**. + +- **LinkedIn:** [Mohamed Yehia](https://www.linkedin.com/in/24-mohamed-yehia/) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1117055 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,47 @@ +{{ bos_token }} +{%- if messages[0]['role'] == 'system' -%} + {%- if messages[0]['content'] is string -%} + {%- set first_user_prefix = messages[0]['content'] + ' + +' -%} + {%- else -%} + {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' + +' -%} + {%- endif -%} + {%- set loop_messages = messages[1:] -%} +{%- else -%} + {%- set first_user_prefix = "" -%} + {%- set loop_messages = messages -%} +{%- endif -%} +{%- for message in loop_messages -%} + {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} + {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }} + {%- endif -%} + {%- if (message['role'] == 'assistant') -%} + {%- set role = "model" -%} + {%- else -%} + {%- set role = message['role'] -%} + {%- endif -%} + {{ '' + role + ' +' + (first_user_prefix if loop.first else "") }} + {%- if message['content'] is string -%} + {{ message['content'] | trim }} + {%- elif message['content'] is iterable -%} + {%- for item in message['content'] -%} + {%- if item['type'] == 'image' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type") }} + {%- endif -%} + {{ ' +' }} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{'model +'}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..30c9ab4 --- /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": "5.6.0", + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5156aa9 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.6.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..9fecd6f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc009274531e24353671373eec4324a05ff3876548a2b33fe9d1aff7632b966 +size 536223056 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..f74d183 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726 +size 33384567 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e27efda --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,26 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "local_files_only": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "" + }, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}