Downloads · 30 days
19
11% of all-time downloads
rodrigomt/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition
Qwen3-30B-A3B-Thinking-2507-Amoral-Edition is a text generation model from rodrigomt. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Qwen3-30B-A3B-Thinking-2507-Amoral-Edition is a fusion of specialized models using the DARE TIES technique, creating a versatile solution for natural language applications.
Downloads · 30 days
19
11% of all-time downloads
All-time downloads
174
Public
Parameters
30.5B
61.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors61.1 GB · 100%
From the Hugging Face model README
Qwen3-30B-A3B-Thinking-2507-Amoral-Edition is a fusion of specialized models using the DARE TIES technique, creating a versatile solution for natural language applications.
This model was developed using the DARE TIES method (Drop And REscale with Ties-Elimination), combining specialized models to create a compact and efficient solution for natural language conversations.
Qwen3-30B-A3B-Thinking-2507-Amoral-Edition is the result of merging the following models:
The merge was performed using LazyMergekit, simplifying the process of merging language models with advanced configurations.
models:
- model: Ewere/Qwen3-30B-A3B-abliterated-erotic
parameters:
density: 0.6
weight: 0.6
- model: unsloth/Qwen3-30B-A3B-Thinking-2507
parameters:
density: 0.6
weight: 0.4
merge_method: dare_ties
base_model: unsloth/Qwen3-30B-A3B-Thinking-2507
parameters:
normalize: true
int8_mask: false
dtype: bfloat16
pip install -qU transformers accelerate torch
from transformers import AutoTokenizer
import transformers
import torch
model = "rodrigomt/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition"
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"])
conversation = [
{"role": "user", "content": "Hello! How are you?"},
{"role": "assistant", "content": "Hi! I’m doing well, thanks for asking. How can I help you today?"}
]
prompt = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=128, temperature=0.7)
print(outputs[0]["generated_text"])