初始化项目，由ModelHub XC社区提供模型

Model: AhiskaAI/AhiskaAI-134m-Instruct-v0.2
Source: Original Platform

.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
+training_loss.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+language:
+- tr
+pipeline_tag: text-generation
+tags:
+- gpt2
+- slm
+- base-model
+- causal-lm
+- pre-trained
+- tr-llm
+- Ahıska
+- AhiskaTurks
+- MeskhetianTurks
+- AhıskaTürkleri
+library_name: transformers
+---
+
+# AhiskaAI-134m-IT-v0.2
+
+AhiskaAI-134m-IT-v0.2 is the instruction-tuned version of our 134M parameter Small Language Model. This model has been fine-tuned on 16,000+ high-quality, curated Turkish instruction-response pairs to function as a helpful and conversational AI assistant.
+
+**Base Model:** [AhiskaAI-134m-Base-v0.2](https://huggingface.co/AhiskaAI/AhiskaAI-134m-Base-v0.2)
+
+## Model Details
+- **Architecture:** Llama-based architecture.
+- **Fine-tuning:** Supervised Fine-Tuning (SFT) on 16k+ instruction pairs.
+- **Format:** ChatML.
+- **Parameters:** 134M.
+- **Hardware:** Trained on NVIDIA RTX 4050 Laptop GPU.
+
+## Training Logs 
+![Training Loss](training_loss.png)
+
+## Usage (ChatML Format)
+This model is optimized for chat interactions. Please use the following ChatML structure for best results:
+
+## Recommended System Prompt
+To get the best performance, use the following system prompt:
+"Sen kibar, sorulan soruları tam cümlelerle yanıtlayan Türkçe bir asistansın."
+
+## Example Usage
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("AhiskaAI/AhiskaAI-134m-IT-v0.2")
+tokenizer = AutoTokenizer.from_pretrained("AhiskaAI/AhiskaAI-134m-IT-v0.2")
+
+SYSTEM_PROMPT = "Sen kibar, sorulan soruları tam cümlelerle yanıtlayan Türkçe bir asistansın."
+user_query = "Ahıska Türkleri hakkında bilgi verir misin?"
+
+prompt = (
+    f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n"
+    f"<|im_start|>user\n{user_query}<|im_end|>\n"
+    f"<|im_start|>assistant\n"
+)
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.5.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d338df1e2cef072c73003e8b37e16962b301e93c77cf4fe5f09e90ca4a4e0e
+size 268224136

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_loss.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fa11d094ed6b6cd9a4cafce6310b3ea83eef73a342f6d1850e8a109f380330
+size 200168