Trinity-33B-v1.0

Trinity

Trinity is a general purpose coding AI. Trinity-33B-v1.0 achieves 70 on HumanEval.

Our Offensive Cybersecurity Model WhiteRabbitNeo-33B-v1.2 model is now in beta!

Check out the Prompt Enhancing feature! Access at: https://www.whiterabbitneo.com/

Join Our Discord Server

Join us at: https://discord.gg/8Ynkrcbk92 (Updated on Dec 29th. Now permanent link to join)

Terms of Use

By accessing and using this Artificial Intelligence (AI) model, you, the user, acknowledge and agree that you are solely responsible for your use of the model and its outcomes. You hereby agree to indemnify, defend, and hold harmless the creators, developers, and any affiliated persons or entities of this AI model from and against any and all claims, liabilities, damages, losses, costs, expenses, fees (including reasonable attorneys' fees and court costs) that may arise, directly or indirectly, from your use of the AI model.

This AI model is provided "as is" and "as available" without any warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement. The creators make no warranty that the AI model will meet your requirements or be available on an uninterrupted, secure, or error-free basis.

Your use of the AI model is at your own risk and discretion, and you will be solely responsible for any damage to computer systems or loss of data that results from the use of the AI model.

This disclaimer constitutes part of the agreement between you and the creators of the AI model regarding your use of the model, superseding any prior agreements between you and the creators regarding your use of this AI model.

Sample Inference Code

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "/home/migel/models/Trinity"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    load_in_8bit=True,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)


def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.5,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    answer = string.split("USER:")[0].strip()
    return f"{answer}"




conversation = f"SYSTEM: You are an AI that can code. Answer with code."


while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}"
    # print(conversation)
    json_data = {"prompt": user_input, "answer": answer}

    # print(json_data)
    # with open(output_file_path, "a") as output_file:
    #     output_file.write(json.dumps(json_data) + "\n")