Update README.md

README.md

@@ -1,63 +0,0 @@
----
-license: apache-2.0
----
-Uses
-
-Important: Please use the exact chat template provided below for the model. Otherwise there will be a degrade in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.
-
-Our model follows the exact chat template and usage as Openchat-3.5-0106. Please refer to their model card for more details. In addition, our model is hosted on LMSYS Chatbot Arena for free test.
-
-The conversation template is the same as Openchat-3.5-0106:
-
-import transformers
-tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat-3.5-0106")
-
-# Single-turn
-tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
-assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
-
-# Multi-turn
-tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
-assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
-
-# Coding Mode
-tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
-assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
-
-Code Examples
-import transformers
-
-tokenizer = transformers.AutoTokenizer.from_pretrained("invalid-coder/Starling-LM-7B-beta-laser-dpo")
-model = transformers.AutoModelForCausalLM.from_pretrained("invalid-coder/Starling-LM-7B-beta-laser-dpo")
-
-def generate_response(prompt):
-    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
-    outputs = model.generate(
-        input_ids,
-        max_length=256,
-        pad_token_id=tokenizer.pad_token_id,
-        eos_token_id=tokenizer.eos_token_id,
-    )
-    response_ids = outputs[0]
-    response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
-    return response_text
-
-# Single-turn conversation
-prompt = "Hello, how are you?"
-single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
-response_text = generate_response(single_turn_prompt)
-print("Response:", response_text)
-
-## Multi-turn conversation
-prompt = "Hello"
-follow_up_question =  "How are you today?"
-response = ""
-multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:"
-response_text = generate_response(multi_turn_prompt)
-print("Multi-turn conversation response:", response_text)
-
-### Coding conversation
-prompt = "Implement quicksort using C++"
-coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:"
-response = generate_response(coding_prompt)
-print("Coding conversation response:", response)