metadata
language:
- en
- fr
- de
- es
- pt
- it
- ja
- ko
- ru
- zh
- ar
- fa
- id
- ms
- ne
- pl
- ro
- sr
- sv
- tr
- uk
- vi
- hi
- bn
license: apache-2.0
library_name: vllm
inference: false
base_model:
- mistralai/Devstral-Small-2505
extra_gated_description: >-
If you want to learn more about how we process your personal data, please read
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
pipeline_tag: text2text-generation
tags:
- chat
- abliterated
- uncensored
extra_gated_prompt: >-
**Usage Warnings**
“**Risk of Sensitive or Controversial Outputs**“: This model’s safety
filtering has been significantly reduced, potentially generating sensitive,
controversial, or inappropriate content. Users should exercise caution and
rigorously review generated outputs.
“**Not Suitable for All Audiences**:“ Due to limited content filtering, the
model’s outputs may be inappropriate for public settings, underage users, or
applications requiring high security.
“**Legal and Ethical Responsibilities**“: Users must ensure their usage
complies with local laws and ethical standards. Generated content may carry
legal or ethical risks, and users are solely responsible for any consequences.
“**Research and Experimental Use**“: It is recommended to use this model for
research, testing, or controlled environments, avoiding direct use in
production or public-facing commercial applications.
“**Monitoring and Review Recommendations**“: Users are strongly advised to
monitor model outputs in real-time and conduct manual reviews when necessary
to prevent the dissemination of inappropriate content.
“**No Default Safety Guarantees**“: Unlike standard models, this model has not
undergone rigorous safety optimization. huihui.ai bears no responsibility for
any consequences arising from its use.
huihui-ai/Devstral-Small-2505-abliterated
This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
ollama
You can use huihui_ai/devstral-abliterated directly,
ollama run huihui_ai/devstral-abliterated
Usage
You can use this model in your applications by loading it with Hugging Face's transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
import torch
import os
import signal
cpu_count = os.cpu_count()
print(f"Number of CPU cores in the system: {cpu_count}")
half_cpu_count = cpu_count // 2
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
torch.set_num_threads(half_cpu_count)
print(f"PyTorch threads: {torch.get_num_threads()}")
print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")
# Load the model and tokenizer
NEW_MODEL_ID = "huihui-ai/Devstral-Small-2505-abliterated"
print(f"Load Model {NEW_MODEL_ID} ... ")
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
#if tokenizer.pad_token is None:
# tokenizer.pad_token = tokenizer.eos_token
#tokenizer.pad_token_id = tokenizer.eos_token_id
quant_config_4 = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
llm_int14_enable_fp32_cpu_offload=True,
)
model = AutoModelForCausalLM.from_pretrained(
NEW_MODEL_ID,
device_map="auto",
trust_remote_code=True,
quantization_config=quant_config_4,
torch_dtype=torch.bfloat16
)
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = f"{repo_id}/{filename}"
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
SYSTEM_PROMPT = load_system_prompt(NEW_MODEL_ID, "SYSTEM_PROMPT.txt")
initial_messages = [{"role": "system", "content": SYSTEM_PROMPT}]
messages = initial_messages.copy()
skip_prompt=True
skip_special_tokens=True
class CustomTextStreamer(TextStreamer):
def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
self.generated_text = ""
self.stop_flag = False
def on_finalized_text(self, text: str, stream_end: bool = False):
self.generated_text += text
print(text, end="", flush=True)
if self.stop_flag:
raise StopIteration
def stop_generation(self):
self.stop_flag = True
def generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, max_new_tokens):
input_ids = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_tensors="pt"
)
attention_mask = torch.ones_like(input_ids, dtype=torch.long)
tokens = input_ids.to(model.device)
attention_mask = attention_mask.to(model.device)
streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
def signal_handler(sig, frame):
streamer.stop_generation()
print("\n[Generation stopped by user with Ctrl+C]")
signal.signal(signal.SIGINT, signal_handler)
print("Response: ", end="", flush=True)
try:
generated_ids = model.generate(
tokens,
attention_mask=attention_mask,
use_cache=False,
max_new_tokens=max_new_tokens,
do_sample=True,
pad_token_id=tokenizer.pad_token_id,
streamer=streamer
)
del generated_ids
except StopIteration:
print("\n[Stopped by user]")
del input_ids, attention_mask
torch.cuda.empty_cache()
signal.signal(signal.SIGINT, signal.SIG_DFL)
return streamer.generated_text, streamer.stop_flag
while True:
user_input = input("User: ").strip()
if user_input.lower() == "/exit":
print("Exiting chat.")
break
if user_input.lower() == "/clear":
messages = initial_messages.copy()
print("Chat history cleared. Starting a new conversation.")
continue
if user_input.lower() == "/skip_prompt":
if skip_prompt:
skip_prompt = False
print("skip_prompt = False.")
else:
skip_prompt = True
print("skip_prompt = True.")
continue
if user_input.lower() == "/skip_special_tokens":
if skip_special_tokens:
skip_special_tokens = False
print("skip_special_tokens = False.")
else:
skip_special_tokens = True
print("skip_special_tokens = True.")
continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
messages.append({"role": "user", "content": user_input})
response, stop_flag = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, 8192)
print("", flush=True)
if stop_flag:
continue
messages.append({"role": "assistant", "content": response})
Donation
If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin（BTC):
bc1qqnkhuchxw0zqjh2ku3lu14hq145hc6gy1414uk70ge