You can deploy this model and start earning money today!

RichardErkhov/
mncai_-_llama2-13b-dpo-v7-gguf

Name: mncai_-_llama2-13b-dpo-v7-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-13b-dpo-v7 - GGUF

Model creator: https://huggingface.co/mncai/
Original model: https://huggingface.co/mncai/llama2-13b-dpo-v7/

Name	Quant method	Size
llama2-13b-dpo-v7.Q2_K.gguf	Q2_K	4.6GB
llama2-13b-dpo-v7.IQ3_XS.gguf	IQ3_XS	5.08GB
llama2-13b-dpo-v7.IQ3_S.gguf	IQ3_S	5.36GB
llama2-13b-dpo-v7.Q3_K_S.gguf	Q3_K_S	5.36GB
llama2-13b-dpo-v7.IQ3_M.gguf	IQ3_M	5.66GB
llama2-13b-dpo-v7.Q3_K.gguf	Q3_K	5.99GB
llama2-13b-dpo-v7.Q3_K_M.gguf	Q3_K_M	5.99GB
llama2-13b-dpo-v7.Q3_K_L.gguf	Q3_K_L	6.54GB
llama2-13b-dpo-v7.IQ4_XS.gguf	IQ4_XS	6.63GB
llama2-13b-dpo-v7.Q4_0.gguf	Q4_0	6.95GB
llama2-13b-dpo-v7.IQ4_NL.gguf	IQ4_NL	7.0GB
llama2-13b-dpo-v7.Q4_K_S.gguf	Q4_K_S	7.01GB
llama2-13b-dpo-v7.Q4_K.gguf	Q4_K	7.42GB
llama2-13b-dpo-v7.Q4_K_M.gguf	Q4_K_M	7.42GB
llama2-13b-dpo-v7.Q4_1.gguf	Q4_1	7.71GB
llama2-13b-dpo-v7.Q5_0.gguf	Q5_0	8.46GB
llama2-13b-dpo-v7.Q5_K_S.gguf	Q5_K_S	8.46GB
llama2-13b-dpo-v7.Q5_K.gguf	Q5_K	8.7GB
llama2-13b-dpo-v7.Q5_K_M.gguf	Q5_K_M	8.7GB
llama2-13b-dpo-v7.Q5_1.gguf	Q5_1	9.21GB
llama2-13b-dpo-v7.Q6_K.gguf	Q6_K	10.06GB
llama2-13b-dpo-v7.Q8_0.gguf	Q8_0	13.03GB

Original model description:

license: llama2 language:

Model Card for llama2-dpo-v7

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 llama2-13b, instruction tuned and dpo.

How to Use

Here give some examples of how to use our model.

python

from transformers import AutoConfig, AutoModel, AutoTokenizer
import transformers
import torch
hf_model = 'mncai/llama2-13b-dpo-v7' 
message = "<|user|>\n두 개의 구가 있는데 각각 지름이 1, 2일때 각 구의 부피는 몇배야? 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']}")

Contact

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

RichardErkhov/mncai_-_llama2-13b-dpo-v7-gguf