Update README.md

README.md

@@ -1,4 +1,65 @@
 ---
 {}
 ---
-mix2 + 30k safety + 15w ultra-interact
+This preference model is trained from [LLaMA3-8B-it](meta-llama/Meta-Llama-3-8B-Instruct) with the training script at [Reward Modeling](https://github.com/RLHFlow/RLHF-Reward-Modeling/tree/pm_dev/pair-pm).
+
+The dataset is RLHFlow/pair_preference_model_dataset. It achieves Chat-98.6, Char-hard 65.8, Safety 89.6, and reasoning 94.9 in reward bench.
+
+
+## Service the RM
+
+Here is an example to use the Preference Model to rank a pair. For n>2 responses, it is recommened to use the tournament style ranking strategy to get the best response so that the complexity is linear in n.
+
+```python
+device = 0
+
+model = AutoModelForCausalLM.from_pretrained(script_args.preference_name_or_path,
+                                             torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2").cuda()
+tokenizer = AutoTokenizer.from_pretrained(script_args.preference_name_or_path, use_fast=True)
+tokenizer_plain = AutoTokenizer.from_pretrained(script_args.preference_name_or_path, use_fast=True)
+tokenizer_plain.chat_template = "\n{% for message in messages %}{% if loop.index0 % 2 == 0 %}\n\n<turn> user\n {{ message['content'] }}{% else %}\n\n<turn> assistant\n {{ message['content'] }}{% endif %}{% endfor %}\n\n\n"
+
+prompt_template = "[CONTEXT] {context} [RESPONSE A] {response_A} [RESPONSE B] {response_B} \n"
+token_id_A = tokenizer.encode("A", add_special_tokens=False)
+token_id_B = tokenizer.encode("B", add_special_tokens=False)
+assert len(token_id_A) == 1 and len(token_id_B) == 1
+token_id_A = token_id_A[0]
+token_id_B = token_id_B[0]
+temperature = 1.0
+
+
+model.eval()
+prompt = "AAAA"
+response_chosen = "BBBB"
+response_rejected = "CCCC"
+
+instruction = [{"role": "user", "content": prompt}]
+context = tokenizer_plain.apply_chat_template(instruction, tokenize=False)
+responses = [response_chosen, response_rejected]
+probs_chosen = []
+    
+for chosen_position in [0, 1]:
+    # we swap order to mitigate position bias
+    response_A = responses[chosen_position]
+    response_B = responses[1 - chosen_position]
+    prompt = prompt_template.format(context=context, response_A=response_A, response_B=response_B)
+    message = [
+        {"role": "user", "content": prompt},
+    ]
+
+    input_ids = tokenizer.encode(tokenizer.apply_chat_template(message, tokenize=False).replace(tokenizer.bos_token, ""), return_tensors='pt', add_special_tokens=False).cuda() 
+
+    with torch.no_grad():
+        output = model(input_ids)
+    logit_A = output.logits[0, -1, token_id_A].item()
+    logit_B = output.logits[0, -1, token_id_B].item()
+    # take softmax to get the probability; using numpy
+    Z = np.exp(logit_A / temperature) + np.exp(logit_B / temperature)
+    logit_chosen = [logit_A, logit_B][chosen_position]
+    prob_chosen = np.exp(logit_chosen / temperature) / Z
+    probs_chosen.append(prob_chosen)
+
+avg_prob_chosen = np.mean(probs_chosen)
+correct = 0.5 if avg_prob_chosen == 0.5 else float(avg_prob_chosen > 0.5)
+print(correct)
+```