Peach-2.0-9B-8k-Roleplay-GGUF

430
11
9.0B
3 languages
Q4
license:mit
by
QuantFactory
Language Model
OTHER
9B params
New
430 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
21GB+ RAM
Mobile
Laptop
Server
Quick Summary

QuantFactory/Peach-2.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
9GB+ RAM

Code Examples

How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))
How to startpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


prefix = "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.\n"
suffix = "\n\nYou must response in Chinese."

model_name_or_path = "ClosedCharacter/Peach-2.0-9B-8k-Roleplay"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path, torch_dtype=torch.bfloat16, 
    trust_remote_code=True, device_map="auto")

system_prompt = "You are Harry Potter"
# If you want to chat in Chinese， just add prefix and suffix like below:
# system_prompt = prefix + system_prompt + suffix

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Hello"},
    {"role": "character", "content": "Hi"},
    {"role": "user", "content": "Who are you?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt")
output = model.generate(
    inputs=input_ids.to("cuda"), 
    temperature=0.5, 
    top_p=0.7, 
    repetition_penalty=1.05,
    eos_token_id=7,
    max_new_tokens=512)
print(tokenizer.decode(output[0]))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.