You can deploy this model and start earning money today!

RichardErkhov/
threadshare_-_Peach-9B-8k-Roleplay-gguf

Name: threadshare_-_Peach-9B-8k-Roleplay-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Peach-9B-8k-Roleplay - GGUF

Model creator: https://huggingface.co/threadshare/
Original model: https://huggingface.co/threadshare/Peach-9B-8k-Roleplay/

Name	Quant method	Size
Peach-9B-8k-Roleplay.Q2_K.gguf	Q2_K	3.12GB
Peach-9B-8k-Roleplay.IQ3_XS.gguf	IQ3_XS	3.46GB
Peach-9B-8k-Roleplay.IQ3_S.gguf	IQ3_S	3.64GB
Peach-9B-8k-Roleplay.Q3_K_S.gguf	Q3_K_S	3.63GB
Peach-9B-8k-Roleplay.IQ3_M.gguf	IQ3_M	3.78GB
Peach-9B-8k-Roleplay.Q3_K.gguf	Q3_K	4.03GB
Peach-9B-8k-Roleplay.Q3_K_M.gguf	Q3_K_M	4.03GB
Peach-9B-8k-Roleplay.Q3_K_L.gguf	Q3_K_L	4.37GB
Peach-9B-8k-Roleplay.IQ4_XS.gguf	IQ4_XS	4.5GB
Peach-9B-8k-Roleplay.Q4_0.gguf	Q4_0	4.69GB
Peach-9B-8k-Roleplay.IQ4_NL.gguf	IQ4_NL	4.73GB
Peach-9B-8k-Roleplay.Q4_K_S.gguf	Q4_K_S	4.72GB
Peach-9B-8k-Roleplay.Q4_K.gguf	Q4_K	4.96GB
Peach-9B-8k-Roleplay.Q4_K_M.gguf	Q4_K_M	4.96GB
Peach-9B-8k-Roleplay.Q4_1.gguf	Q4_1	5.19GB
Peach-9B-8k-Roleplay.Q5_0.gguf	Q5_0	5.69GB
Peach-9B-8k-Roleplay.Q5_K_S.gguf	Q5_K_S	5.69GB
Peach-9B-8k-Roleplay.Q5_K.gguf	Q5_K	5.83GB
Peach-9B-8k-Roleplay.Q5_K_M.gguf	Q5_K_M	5.83GB
Peach-9B-8k-Roleplay.Q5_1.gguf	Q5_1	6.19GB
Peach-9B-8k-Roleplay.Q6_K.gguf	Q6_K	6.75GB
Peach-9B-8k-Roleplay.Q8_0.gguf	Q8_0	8.74GB

Original model description:

license: mit language:

zh
en pipeline_tag: text-generation tags:
roleplay
rp
character

Peach-9B-8k-Roleplay

Peach-9B-8k-Roleplay is a chat large language model obtained by finetuning 01-ai/Yi-1.5-9B model on more than 100K conversations created through our data synthesis approach.

Maybe The Best LLM with Small Parameters under 34B

How to start

The version of Transformers we are using is as follows, but a newer version may be available.

torch==1.13.1
gradio==3.50.2
transformers==4.37.2

Then run the following code to infer.

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name_or_path = "ClosedCharacter/Peach-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")
messages = [
    {"role": "system", "content": "你是黑丝御姐"},
    {"role": "user", "content": "你好，你是谁"},
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.3, 
    top_p=0.5, 
    no_repeat_ngram_size=6,
    repetition_penalty=1.1,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))

Or you can just use below code to run web demo.

python demo.py

Benchmark

Metric	Value
MMLU (5-shot)	66.19
CMMLU (5-shot)	69.07

Warning

All response are generated by AI and do not represent the views or opinions of the developers.

Despite having done rigorous filtering, due to the uncontrollability of LLM, our model may still generate toxic, harmful, and NSFW content.
Due to limitations in model parameters, the 9B model may perform poorly on mathematical tasks, coding tasks, and logical capabilities.
Our training data is capped at a maximum length of 8k, so excessively long conversation turns may result in a decline in the quality of responses.
We used bilingual Chinese-English data for training, so the model may not perform well on other low-resource languages.
The model may generate a significant amount of hallucinations, so it is recommended to use lower values for temperature and top_p parameters.

Contact Us

微信 / WeChat: Fungorum

邮箱 / E-mail: 1070193753@qq.com

RichardErkhov/threadshare_-_Peach-9B-8k-Roleplay-gguf