README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-13b-dpo-v3 - GGUF

• Model creator: https://huggingface.co/mncai/
• Original model: https://huggingface.co/mncai/llama2-13b-dpo-v3/

Name	Quant method	Size
llama2-13b-dpo-v3.Q2_K.gguf	Q2_K	4.6GB
llama2-13b-dpo-v3.IQ3_XS.gguf	IQ3_XS	5.08GB
llama2-13b-dpo-v3.IQ3_S.gguf	IQ3_S	5.36GB
llama2-13b-dpo-v3.Q3_K_S.gguf	Q3_K_S	5.36GB
llama2-13b-dpo-v3.IQ3_M.gguf	IQ3_M	5.66GB
llama2-13b-dpo-v3.Q3_K.gguf	Q3_K	5.99GB
llama2-13b-dpo-v3.Q3_K_M.gguf	Q3_K_M	5.99GB
llama2-13b-dpo-v3.Q3_K_L.gguf	Q3_K_L	6.54GB
llama2-13b-dpo-v3.IQ4_XS.gguf	IQ4_XS	6.63GB
llama2-13b-dpo-v3.Q4_0.gguf	Q4_0	6.95GB
llama2-13b-dpo-v3.IQ4_NL.gguf	IQ4_NL	7.0GB
llama2-13b-dpo-v3.Q4_K_S.gguf	Q4_K_S	7.01GB
llama2-13b-dpo-v3.Q4_K.gguf	Q4_K	7.42GB
llama2-13b-dpo-v3.Q4_K_M.gguf	Q4_K_M	7.42GB
llama2-13b-dpo-v3.Q4_1.gguf	Q4_1	7.71GB
llama2-13b-dpo-v3.Q5_0.gguf	Q5_0	8.46GB
llama2-13b-dpo-v3.Q5_K_S.gguf	Q5_K_S	8.46GB
llama2-13b-dpo-v3.Q5_K.gguf	Q5_K	8.7GB
llama2-13b-dpo-v3.Q5_K_M.gguf	Q5_K_M	8.7GB
llama2-13b-dpo-v3.Q5_1.gguf	Q5_1	9.21GB
llama2-13b-dpo-v3.Q6_K.gguf	Q6_K	10.06GB
llama2-13b-dpo-v3.Q8_0.gguf	Q8_0	13.03GB

Original model description:

license: cc-by-nc-sa-4.0 language: - en - ko

Model Card for llama2-dpo-v3

Introduction of MindsAndCompany

https://mnc.ai/

We develop a diverse range of AI models and craft solutions tailored for business applications. In the realm of generative AI, our product development includes the Code Assistant, the TOD Chatbot, and LLMOps. We are also actively working on the development of Enterprise AGI (Artificial General Intelligence).

Model Summary

based beomi/llama-2-koen-13b, instruction tuned and dpo.

How to Use

Here give some examples of how to use our model.

from transformers import AutoConfig, AutoModel, AutoTokenizer
import transformers
import torch
hf_model = 'mncai/llama2-13b-dpo-v3' 
message = "<|user|>\n두 개의 구가 있는데 각각 지름이 1, 2일때 구의 부피는 몇배 차이가 나지? 설명도 같이 해줘.\n<|assistant|>\n"

sequences = pipeline(
    message,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=2048,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

LICENSE

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under LLAMA 2 COMMUNITY LICENSE AGREEMENT

Contact

If you have any questions, please raise an issue or contact us at dwmyoung@mnc.ai