Update README.md

README.md

@@ -8,6 +8,8 @@ tags:
 - alpaca
 - bloom
 - LLM
+datasets:
+- tatsu-lab/alpaca
 ---
 
 # AlpacOOM: Alpaca + BLOOM
@@ -45,5 +47,79 @@ TBA
 
 ## How to use
 ```py
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
+peft_model_id = "mrm8488/Alpacoom"
+config = PeftConfig.from_pretrained(peft_model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-7b1")
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+model = PeftModel.from_pretrained(model, peft_model_id)
+model.eval()
+
+# Based on the inference code by `tloen/alpaca-lora`
+def generate_prompt(instruction, input=None):
+    if input:
+        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+### Instruction:
+{instruction}
+### Input:
+{input}
+### Response:"""
+    else:
+        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
+### Instruction:
+{instruction}
+### Response:"""
+
+def generate(
+        instruction,
+        input=None,
+        temperature=0.1,
+        top_p=0.75,
+        top_k=40,
+        num_beams=4,
+        **kwargs,
+):
+    prompt = generate_prompt(instruction, input)
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].cuda()
+    generation_config = GenerationConfig(
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        num_beams=num_beams,
+        **kwargs,
+    )
+    with torch.no_grad():
+        generation_output = model.generate(
+            input_ids=input_ids,
+            generation_config=generation_config,
+            return_dict_in_generate=True,
+            output_scores=True,
+            max_new_tokens=256,
+        )
+    s = generation_output.sequences[0]
+    output = tokenizer.decode(s)
+    return output.split("### Response:")[1].strip().split("Below")[0]
+
+instruction = "Tell me about alpacas"
+
+print("Instruction:", instruction)
+print("Response:", generate(instruction))
+```
+
+## Citation
+```
+@misc {manuel_romero_2023,
+	author       = { {Manuel Romero} },
+	title        = { Alpacoom (Revision 874f989) },
+	year         = 2023,
+	url          = { https://huggingface.co/mrm8488/Alpacoom },
+	doi          = { 10.57967/hf/0449 },
+	publisher    = { Hugging Face }
+}
 ```