From c7848d76620e0e9debd4bb4d87255d7d90de0170 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 25 May 2026 21:25:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Rudblest/projedanismanai Source: Original Platform --- .gitattributes | 37 +++++++++ README.md | 105 +++++++++++++++++++++++++ config.json | 30 +++++++ generation_config.json | 6 ++ mistral-nemo-instruct-2407.Q4_K_M.gguf | 3 + model.safetensors | 3 + tokenizer.json | 3 + tokenizer_config.json | 13 +++ 8 files changed, 200 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 mistral-nemo-instruct-2407.Q4_K_M.gguf create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be62391 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +mistral-nemo-instruct-2407.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..34332b8 --- /dev/null +++ b/README.md @@ -0,0 +1,105 @@ +--- +language: +- tr +license: apache-2.0 +base_model: mistralai/Mistral-Nemo-Instruct-2407 +tags: +- mistral +- turkish +- teknofest +- tubitak +- fine-tuned +- qlora +- unsloth +pipeline_tag: text-generation +--- + +# ProjeDanışmanAi + +**TEKNOFEST ve TÜBİTAK yarışmacıları için Türkçe yapay zeka danışmanı.** + +Mistral-Nemo-Instruct-2407 (12B) modeli, TEKNOFEST ve TÜBİTAK yarışma süreçlerine özel Türkçe veri setiyle fine-tune edilmiştir. + +--- + +## Model Detayları + +| Özellik | Değer | +|---|---| +| Temel Model | mistralai/Mistral-Nemo-Instruct-2407 | +| Yöntem | QLoRA 4-bit + unsloth | +| LoRA Rank | 64 (alpha=128, rsLoRA=True) | +| Eğitim Verisi | 3043 Türkçe instruction-output çifti | +| Epoch | 5 | +| Max Seq Length | 3072 | +| Train Loss | 0.3591 | + +--- + +## Kullanım Alanları + +- TEKNOFEST KTR/PTR teknik rapor yazımı +- TÜBİTAK başvuru hazırlığı +- Proje fikri netleştirme +- Risk analizi ve uygulanabilirlik değerlendirmesi +- Başlık ve özet üretimi +- Jüri ve sunum hazırlığı + +--- + +## Veri Seti + +3043 Türkçe örnekten oluşan özel veri seti: + +| Kategori | Örnek Sayısı | +|---|---| +| rapor_yazimi | 761 | +| sifirdan_proje | 730 | +| genel_ozet | 593 | +| strateji | 505 | +| hata_duzeltme | 324 | +| red (alan dışı red) | 130 | + +--- + +## Kullanım + +### GGUF (Ollama ile) + +```bash +ollama create projedanismanai -f Modelfile +ollama run projedanismanai +``` + +### Python (unsloth ile) + +```python +from unsloth import FastLanguageModel + +model, tokenizer = FastLanguageModel.from_pretrained( + model_name = "Rudblest/projedanismanai", + max_seq_length = 3072, + dtype = None, + load_in_4bit = True, +) +FastLanguageModel.for_inference(model) + +prompt = "[INST] TEKNOFEST KTR raporunda risk analizi nasıl yazılır? [/INST] " +inputs = tokenizer(prompt, return_tensors="pt").to("cuda") +output = model.generate(**inputs, max_new_tokens=512, temperature=0.7) +print(tokenizer.decode(output[0], skip_special_tokens=True)) +``` + +--- + +## Sınırlamalar + +- Yalnızca Türkçe cevap verir +- Alan dışı sorular (yemek, borsa, sağlık vb.) reddedilir +- TEKNOFEST/TÜBİTAK dışı mühendislik konularında performans düşebilir + +--- + +## Lisans + +Apache 2.0 — Mistral-Nemo temel modeli lisansına uygun. diff --git a/config.json b/config.json new file mode 100644 index 0000000..468c622 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.5.0", + "use_cache": true, + "vocab_size": 131072 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b7715d4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "5.5.0" +} diff --git a/mistral-nemo-instruct-2407.Q4_K_M.gguf b/mistral-nemo-instruct-2407.Q4_K_M.gguf new file mode 100644 index 0000000..9353383 --- /dev/null +++ b/mistral-nemo-instruct-2407.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20acec0de1a0e9b4b8f6e0f7dfdc3c83a7825d6970e7d87aef31f08f6367d68f +size 7477207456 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..8f68e8f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8da20a04b7ad093b1e4079f74177cb365fe822ffadb2414cc61036e2cf54d54 +size 24495607560 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..4e74d59 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2 +size 17078292 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d2c21cd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,13 @@ +{ + "add_prefix_space": false, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "" +} \ No newline at end of file