Update README.md

README.md

@@ -22,7 +22,84 @@ This model is a fine-tuned version of [meta-llama/Llama-2-13b-chat-hf](https://h
 
 
 ## Intended uses & limitations
+```
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM,AutoTokenizer
+```
+Loading Tokenizer
+```
+model_id = "meta-llama/Llama-2-13b-chat-hf"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer.pad_token = tokenizer.eos_token
+```
+Loading Model
+```
+config = PeftConfig.from_pretrained("zera09/llama_FT")
+base_model = AutoModelForCausalLM.from_pretrained(model_id,load_in_4bit=True, device_map='cuda')
+model = PeftModel.from_pretrained(base_model, "zera09/llama_FT")
+```
 
+Template for inference
+```
+template = """### Instruction
+Given this context: {context} and price:{price}output onle one decision from the square bracket [buy,sell,hold] and provide reasoning om why.
+
+### Response:
+Decision:
+Reasonong:
+```"""
+```
+```
+from transformers import set_seed
+
+
+def gen(text):
+    toks = tokenizer(text, return_tensors="pt").to("cuda")
+
+    set_seed(32)
+    model.eval()
+    with torch.no_grad():
+        out = model.generate(
+            **toks,
+            max_new_tokens=350,
+            top_k=5,
+            do_sample=True,
+        )
+    return tokenizer.decode(
+        out[0][len(toks["input_ids"][0]) :], skip_special_tokens=True
+    )
+```
+
+Runign Inference On single text
+```
+context = "The global recloser control market is expected to grow significantly, driven by increasing demand for power quality and reliability, especially in the electric segment and emerging economies like China. The positive score for this news is 1.1491235518690246e-08. The neutral score for this news is 0.9999998807907104. The negative score for this news is 6.358970239261907e-08"
+price = str(12.1)
+print(gen(template.format(context=news,price=price)).split("```"))
+```
+
+For multiple text
+```
+import pandas as pd
+
+data = panda.read_pickle('./DRIV_train.pkl')
+data = pd.DataFrame(data).T
+
+model.eval()
+answer_list = []
+for idx,row in ans_sum.iterrows():
+  toks = tokenizer(template.format(context=row['news']['DRIV'][0],price=str(row['price']['DRIV'][0]))), return_tensors="pt").to("cuda")
+    with torch.no_grad():
+      out = model.generate(
+        **toks,
+        max_new_tokens=350,
+        top_k=5,
+        do_sample=True,
+      )
+        
+    ans_list.append(tokenizer.decode(
+                out[0][len(toks["input_ids"][0]) :], skip_special_tokens=True
+                )
+```
 
 ### Training hyperparameters