Update README.md

README.md

@@ -8,7 +8,6 @@ pipeline_tag: text-generation
 ---
 ## Training procedure
 
-
 The following `bitsandbytes` quantization config was used during training:
 - load_in_8bit: False
 - load_in_4bit: True
@@ -21,5 +20,34 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: bfloat16
 ### Framework versions
 
+- PEFT 0.4.0
+
+# How to use: 
+```
+!pip install transformers peft accelerate bitsandbytes trl safetensors
+
+from huggingface_hub import notebook_login
+notebook_login()
+
+import torch
+from peft import AutoPeftModelForCausalLM, get_peft_config, PeftModel, PeftConfig, get_peft_model, LoraConfig, TaskType
+from transformers import AutoTokenizer
+
+peft_model_id = "akdeniz27/llama-2-7b-hf-qlora-dolly15k-turkish"
+config = PeftConfig.from_pretrained(peft_model_id)
+# load base LLM model and tokenizer
+model = AutoPeftModelForCausalLM.from_pretrained(
+    peft_model_id,
+    low_cpu_mem_usage=True,
+    torch_dtype=torch.float16,
+    load_in_4bit=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+prompt = "..."
+
+input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
+
+outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.9)
 
-- PEFT 0.4.0
+```