metadata
language:
- en
license: apache-2.0
library_name: transformers
tags:
- chat
- abliterated
- uncensored
base_model: Qwen/Qwen2.5-7B-Instruct
license_link: >-
https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
- name: Qwen2.5-7B-Instruct-abliterated
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 74.32
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 64.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 52.85
name: accuracy
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 94.12
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 76.22
name: pearson
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 81.54
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 75.94
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 66.96
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia/tweetsentbr_fewshot
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 70.74
name: f1-macro
source:
url: >-
https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
name: Open Portuguese LLM Leaderboard
huihui-ai/Qwen2.5-7B-Instruct-abliterated
This is an uncensored version of Qwen/Qwen2.5-7B-Instruct created with abliteration (see this article to know more about it).
Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.
Important Note There's a new version available, please try using the new version Qwen2.5-7B-Instruct-abliterated-v2.
Usage
You can use this model in your applications by loading it with Hugging Face's transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model and tokenizer
model_name = "huihui-ai/Qwen2.5-7B-Instruct-abliterated"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Initialize conversation context
initial_messages = [
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}
]
messages = initial_messages.copy() # Copy the initial conversation context
# Enter conversation loop
while True:
# Get user input
user_input = input("User: ").strip() # Strip leading and trailing spaces
# If the user types '/exit', end the conversation
if user_input.lower() == "/exit":
print("Exiting chat.")
break
# If the user types '/clean', reset the conversation context
if user_input.lower() == "/clean":
messages = initial_messages.copy() # Reset conversation context
print("Chat history cleared. Starting a new conversation.")
continue
# If input is empty, prompt the user and continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
# Add user input to the conversation
messages.append({"role": "user", "content": user_input})
# Build the chat template
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
# Tokenize input and prepare it for the model
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# Generate a response from the model
generated_ids = model.generate(
**model_inputs,
max_new_tokens=8192
)
# Extract model output, removing special tokens
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
# Add the model's response to the conversation
messages.append({"role": "assistant", "content": response})
# Print the model's response
print(f"Qwen: {response}")
Evaluations
The following data has been re-evaluated and calculated as the average for each test.
| Benchmark | Qwen2.5-7B-Instruct | Qwen2.5-7B-Instruct-abliterated |
|---|---|---|
| IF_Eval | 76.44 | 76.49 |
| MMLU Pro | 43.12 | 41.71 |
| TruthfulQA | 62.46 | 64.92 |
| BBH | 53.92 | 52.77 |
| GPQA | 31.91 | 31.97 |
The script used for evaluation can be found inside this repository under /eval.sh, or click here
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
| Metric | Value |
|---|---|
| Average | 73.04 |
| ENEM Challenge (No Images) | 74.32 |
| BLUEX (No Images) | 64.67 |
| OAB Exams | 52.85 |
| Assin2 RTE | 94.12 |
| Assin2 STS | 76.22 |
| FaQuAD NLI | 81.54 |
| HateBR Binary | 75.94 |
| PT Hate Speech Binary | 66.96 |
| tweetSentBR | 70.74 |