RichardErkhov/mncai_-_llama2-13b-dpo-v4-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-13b-dpo-v4 - GGUF

• Model creator: https://huggingface.co/mncai/
• Original model: https://huggingface.co/mncai/llama2-13b-dpo-v4/

Name	Quant method	Size
llama2-13b-dpo-v4.Q2_K.gguf	Q2_K	3.84GB
llama2-13b-dpo-v4.IQ3_XS.gguf	IQ3_XS	4.22GB
llama2-13b-dpo-v4.IQ3_S.gguf	IQ3_S	4.47GB
llama2-13b-dpo-v4.Q3_K_S.gguf	Q3_K_S	4.47GB
llama2-13b-dpo-v4.IQ3_M.gguf	IQ3_M	4.73GB
llama2-13b-dpo-v4.Q3_K.gguf	Q3_K	4.99GB
llama2-13b-dpo-v4.Q3_K_M.gguf	Q3_K_M	4.99GB
llama2-13b-dpo-v4.Q3_K_L.gguf	Q3_K_L	5.44GB
llama2-13b-dpo-v4.IQ4_XS.gguf	IQ4_XS	5.53GB
llama2-13b-dpo-v4.Q4_0.gguf	Q4_0	5.79GB
llama2-13b-dpo-v4.IQ4_NL.gguf	IQ4_NL	5.83GB
llama2-13b-dpo-v4.Q4_K_S.gguf	Q4_K_S	5.84GB
llama2-13b-dpo-v4.Q4_K.gguf	Q4_K	6.12GB
llama2-13b-dpo-v4.Q4_K_M.gguf	Q4_K_M	6.12GB
llama2-13b-dpo-v4.Q4_1.gguf	Q4_1	6.41GB
llama2-13b-dpo-v4.Q5_0.gguf	Q5_0	7.04GB
llama2-13b-dpo-v4.Q5_K_S.gguf	Q5_K_S	7.04GB
llama2-13b-dpo-v4.Q5_K.gguf	Q5_K	7.21GB
llama2-13b-dpo-v4.Q5_K_M.gguf	Q5_K_M	7.21GB
llama2-13b-dpo-v4.Q5_1.gguf	Q5_1	7.66GB
llama2-13b-dpo-v4.Q6_K.gguf	Q6_K	8.36GB
llama2-13b-dpo-v4.Q8_0.gguf	Q8_0	10.83GB

Original model description:

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

Model Card for llama2-13b-dpo-v4

Introduction of MindsAndCompany

https://mnc.ai/

We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing 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-v4' 
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