ctranslate2-4you/InternLM3-8b-Instruct-ct2-int8

Ctranslate2 conversion of InternLM3 - 8b into "int8"

Original model here

Example Usage

Non-Streaming Example:

import ctranslate2
from transformers import AutoTokenizer

def generate_response(prompt: str, system_message: str, model_path: str) -> str:
    generator = ctranslate2.Generator(
        model_path,
        device="cuda",
        compute_type="int8"
    )
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    formatted_prompt = f"""<s><|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
"""
    tokens = tokenizer.tokenize(formatted_prompt, trust_remote_code=True)
    results = generator.generate_batch(
        [tokens],
        max_length=1024,
        sampling_temperature=0.7,
        include_prompt_in_result=False,
        end_token="<|im_end|>",
        return_end_token=False,
    )
    response = tokenizer.decode(results[0].sequences_ids[0], skip_special_tokens=True)
    return response

if __name__ == "__main__":
    model_path = "path/to/your/phi-4-ct2-model"
    system_message = "You are a helpful AI assistant."
    user_prompt = "Write a short poem about a cat."
    response = generate_response(user_prompt, system_message, model_path)
    print("\nGenerated response:")
    print(response)