commit 56391784ee2be975a3fe05e68732215d0fbb58b0 Author: ModelHub XC Date: Mon Sep 28 16:41:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mamediarrafaye/qwen-senegal-generation 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..7f8cdfb --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +language: +- fr +- wo +tags: +- text-generation +- senegal +- wolof +- french +- code-switching +- qwen +- qwen2.5 +license: apache-2.0 +--- + +# Qwen2.5-3B Sénégal Generation + +Modèle de génération de texte en **français sénégalais** avec code-switching Wolof-Français, spécialisé dans la conversation quotidienne sénégalaise. + +## Description + +Ce modèle est un fine-tuning de Qwen2.5-3B-Instruct sur un corpus de 9507 segments de français sénégalais authentique avec insertions naturelles de mots wolof. Il est spécialisé dans les conversations du quotidien : mobilité urbaine, mobile money, cybersécurité, vie universitaire sénégalaise, et interactions sociales au Sénégal. + +## Utilisation + +Le modèle suit le format Question/Réponse de son corpus d'entraînement : + +\`\`\`python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model = AutoModelForCausalLM.from_pretrained( + "mamediarrafaye/qwen-senegal-generation", + torch_dtype=torch.float16, + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained( + "mamediarrafaye/qwen-senegal-generation" +) + +def generer(message, max_new_tokens=150): + # Format obligatoire : Question/Réponse (format du corpus) + formatted = f"Question : {message}\nRéponse :" + + inputs = tokenizer(formatted, return_tensors="pt").to(model.device) + with torch.no_grad(): + outputs = model.generate( + **inputs, + max_new_tokens=max_new_tokens, + temperature=0.7, + top_p=0.9, + do_sample=True, + repetition_penalty=1.2, + pad_token_id=tokenizer.eos_token_id, + ) + response = tokenizer.decode(outputs[0], skip_special_tokens=True) + return response.split("Réponse :")[-1].strip() + +## Domaines couverts + +- Vie universitaire sénégalaise (examens, mémoires, bourses, inscriptions) +- Mobile money (Wave, Orange Money, transferts) +- Cybersécurité et phishing +- Transport urbain (BRT, Car Rapide, TER) +- ASR et développement logiciel +- Interactions sociales quotidiennes au Sénégal + +## Format d'entrée + +Le modèle attend le format suivant : +\`\`\` +Question : [votre message] +Réponse : +\`\`\` + + + +## Données + +- 9507 segments de français sénégalais authentique +- 26% code-switching Wolof-Français +- 74% français sénégalais standard +- Sources : conversations simulées de contexte étudiant sénégalais + +## Entraînement + +- Modèle de base : Qwen2.5-3B-Instruct +- Méthode : LoRA fine-tuning (r=64) +- Epochs : 3 +- Learning rate : 2e-4 +- Framework : TRL/SFTTrainer + +## Exemples de sorties + +| Question | Réponse générée | +|----------|----------------| +| Gayi, qui a de la monnaie pour le taxi ? | Amoul problème, j'ai des billets cassés, je gère la course. | +| Lu bess ? Le guichet automatique est en panne ? | Ah dédet, amoul solo, il y a juste une queue interminable dehors. | +| Nanga def ? Les données sont bien anonymisées ? | Amoul problème, toutes les informations sensibles ont été effacées. | +| Gayi, on fait la réunion à quelle heure ? | On se capte sur Google Meet vers 18h, le temps que tout le monde rentre. | + +## Limitations + +- Spécialisé dans les conversations du quotidien sénégalais — ne pas utiliser pour des questions générales hors domaine +- Performances optimales avec le format Question/Réponse du corpus + diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..e926958 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "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", + "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": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "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": "5.12.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..ded3a63 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.12.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..cfbe913 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edb3954d33cc441cf00f2b80f4b228b174c39ab3f98c510ab89b8a083c5b9ad +size 6171926680 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..866c19a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}