Update README.md

README.md

@@ -12,6 +12,84 @@ Builds on the falcon 7b instruct shared model, the specific model is linked in t
 Trained using this [mental health dataset](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations)
 
 
+How to test the model
+
+```
+import json
+import os
+from pprint import pprint
+import bitsandbytes as bnb
+import torch
+import torch.nn as nn
+import transformers
+from datasets import load_dataset
+from huggingface_hub import notebook_login
+from peft import (
+    LoraConfig,
+    PeftConfig,
+    PeftModel,
+    get_peft_model,
+    prepare_model_for_kbit_training
+)
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig
+)
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+PEFT_MODEL = "akumar23/mental-falcon-7b"
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+config = PeftConfig.from_pretrained(PEFT_MODEL)
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path,
+    return_dict=True,
+    quantization_config=bnb_config,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+tokenizer=AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+tokenizer.pad_token = tokenizer.eos_token
+
+model = PeftModel.from_pretrained(model, PEFT_MODEL)
+
+generation_config = model.generation_config
+generation_config.max_new_tokens = 200
+generation_config.temperature = 0.7
+generation_config.top_p = 0.7
+generation_config.num_return_sequences = 1
+generation_config.pad_token_id = tokenizer.eos_token_id
+generation_config.eos_token_id = tokenizer.eos_token_id
+
+device = "cuda:0"
+
+prompt = """
+<human>: how do i know if i am depressed
+<assistant>:
+""".strip()
+
+encoding = tokenizer(prompt, return_tensors="pt").to(device)
+with torch.inference_mode():
+  outputs = model.generate(
+      input_ids = encoding.input_ids,
+      attention_mask = encoding.attention_mask,
+      generation_config = generation_config
+  )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+
 ## Model Details
 
 ### Model Description