You can deploy this model and start earning money today!

RichardErkhov/
Ppoyaa_-_LuminRP-7B-128k-v0.2-gguf

Name: Ppoyaa_-_LuminRP-7B-128k-v0.2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LuminRP-7B-128k-v0.2 - GGUF

Model creator: https://huggingface.co/Ppoyaa/
Original model: https://huggingface.co/Ppoyaa/LuminRP-7B-128k-v0.2/

Name	Quant method	Size
LuminRP-7B-128k-v0.2.Q2_K.gguf	Q2_K	2.53GB
LuminRP-7B-128k-v0.2.IQ3_XS.gguf	IQ3_XS	2.81GB
LuminRP-7B-128k-v0.2.IQ3_S.gguf	IQ3_S	2.96GB
LuminRP-7B-128k-v0.2.Q3_K_S.gguf	Q3_K_S	2.95GB
LuminRP-7B-128k-v0.2.IQ3_M.gguf	IQ3_M	3.06GB
LuminRP-7B-128k-v0.2.Q3_K.gguf	Q3_K	3.28GB
LuminRP-7B-128k-v0.2.Q3_K_M.gguf	Q3_K_M	3.28GB
LuminRP-7B-128k-v0.2.Q3_K_L.gguf	Q3_K_L	3.56GB
LuminRP-7B-128k-v0.2.IQ4_XS.gguf	IQ4_XS	3.67GB
LuminRP-7B-128k-v0.2.Q4_0.gguf	Q4_0	3.83GB
LuminRP-7B-128k-v0.2.IQ4_NL.gguf	IQ4_NL	3.87GB
LuminRP-7B-128k-v0.2.Q4_K_S.gguf	Q4_K_S	3.86GB
LuminRP-7B-128k-v0.2.Q4_K.gguf	Q4_K	4.07GB
LuminRP-7B-128k-v0.2.Q4_K_M.gguf	Q4_K_M	4.07GB
LuminRP-7B-128k-v0.2.Q4_1.gguf	Q4_1	4.24GB
LuminRP-7B-128k-v0.2.Q5_0.gguf	Q5_0	4.65GB
LuminRP-7B-128k-v0.2.Q5_K_S.gguf	Q5_K_S	4.65GB
LuminRP-7B-128k-v0.2.Q5_K.gguf	Q5_K	4.78GB
LuminRP-7B-128k-v0.2.Q5_K_M.gguf	Q5_K_M	4.78GB
LuminRP-7B-128k-v0.2.Q5_1.gguf	Q5_1	5.07GB
LuminRP-7B-128k-v0.2.Q6_K.gguf	Q6_K	5.53GB
LuminRP-7B-128k-v0.2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

tags:

merge
mergekit
lazymergekit license: apache-2.0

LuminRP-7B-128k-v0.2

LuminRP-7B-128k-v0.2 is a merge of four RP models into one using LazyMergekit. This is a model that is purely for roleplaying and uses a context window of 128k.

Example Response:

I use the ChatML template for this with Instruct Mode enabled. Mistral template is okay to use as well, but I don't recommend Alpaca-Roleplay because it just keeps going. Most likely because the Alpaca-Roleplay template doesn't have a message suffix.

Quantized Version

GGUF: Ppoyaa/LuminRP-7B-128k-v0.2-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Metric	Value
Avg.	73.18
AI2 Reasoning Challenge (25-Shot)	70.56
HellaSwag (10-Shot)	87.46
MMLU (5-Shot)	64.92
TruthfulQA (0-shot)	65.78
Winogrande (5-shot)	82.40
GSM8k (5-shot)	67.93

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/LuminRP-7B-128k-v0.2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

RichardErkhov/Ppoyaa_-_LuminRP-7B-128k-v0.2-gguf