Create README.md

README.md

@@ -0,0 +1,88 @@
+---
+license: cc-by-nc-4.0
+language:
+- tr
+pipeline_tag: question-answering
+---
+
+# Model Card for Model ID
+
+
+gemma-2b-tr fine-tuned with Turkish Instruction-Response pairs.
+
+
+## Restrictions
+
+Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms
+Please refer to the gemma use restrictions before start using the model.
+https://ai.google.dev/gemma/terms#3.2-use
+
+## Using model
+
+```Python
+import torch,re
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "erythropygia/Gemma2b-Turkish-Instruction"
+
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
+tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True, padding_side="left")
+
+def get_completion(query: str, model, tokenizer) -> str:
+  device = "cuda:0"
+
+  prompt_template = """
+  <start_of_turn>user
+  Alt satırdaki soruya cevap ver:\n
+  {query}
+  <end_of_turn>\n<start_of_turn>model
+  """
+  prompt = prompt_template.format(query=query)
+
+  encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
+
+  model_inputs = encodeds.to(device)
+
+
+  #max_new_tokens = 200, temperature = 0.9, repetition_penalty = 0.5,  disabled
+  #num_return_sequences=1, max_length = 256,
+  generated_ids = model.generate(**model_inputs, max_new_tokens = 256, do_sample=True, pad_token_id=tokenizer.eos_token_id)
+  # decoded = tokenizer.batch_decode(generated_ids)
+  decoded = tokenizer.decode(generated_ids[0], skip_special_tokens=False)
+  # Kapanmamış etiketleri silmek için düzenli ifade kullanma
+
+  decoded = re.sub(r'<(end_of_turn|start_of_turn|eos|bos)>[^<]*$', '', decoded)
+
+  decoded = re.sub(r'<(end_of_turn|start_of_turn|eos|bos)>', '', decoded)
+
+  return decoded.strip()
+
+result = get_completion(query="int türünde üç parametre alan ve bunların toplamını döndüren bir işlev oluşturun.", model=model, tokenizer=tokenizer)
+print(result)
+```
+
+
+## Training Details
+
+### Training Data
+
+- Dataset size: ~75k instruction-response pair.
+
+### Training Procedure
+
+#### Training Hyperparameters
+
+- **Epochs:** 1
+- **Context length:** 1024
+- **LoRA Rank:** 32
+- **LoRA Alpha:** 64
+- **LoRA Dropout:** 0.05