The model card, file list, and checksums are here. Have the files and permission to share them? Submit a torrent so others can download from peers.
Getting the source files requires Hugging Face approval.⚡ Why Genesis project exists? Here link that explain everything.
⚡ https://web.tribute.tg/d/KIH ⚡ If you like this Genesis LLM release you can donate to me via @Tribute bot in Telegram messenger and support future Genesis LLM development.
Key diffrence is data reconstruction with noise supression in ssm_out.weight, attn_output.weight, attn_gate.weight, attn_qkv.weight, attn_q.weight, attn_k.weight, attn_v.weight tensors via SVD with preserved training data.
Mine approach based on data reconstruction in model via mathematical statistics. I don't train models, I repair signal in them instead. I scan blocks in model via chunks via 3 parameters and pick best one that fits to weight distribution in tensor. Best picked chunk replaces zero chunks in broken tensor without touching learned structure. Scanning works on tensors with same name and shape. ssm_conv1d tensors are fixed per block. I scan all ssm_conv1d tensors weight and scale distribution and normalize scale for weights only for too loud tensors.
Model is based on HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive base.
And DJLougen/hermes-qwen3.5-35b-a3b-GGUF finetune for Hermes agent.
Join the Discord for updates, roadmaps, projects, or just to chat.
Base model. HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive- 0/465 refusals.
Thanks to HauhauCS
Ready to use. Recommended quant: APEX or Q8_K_P
Tensor drift repair by me. Method: Genesis-SVD
Links:
LLM models often have:
My approach fixes all of that without retraining - pure numerical surgery on the raw bytes of the file.
Quantization script available here: https://pastebin.com/hXhcMJn9
Feel free to do your own quants if you want.
Contact: luffythefox@mail.ru
My Telegram: @LuffyTheFox
Chat template: chat_template.jinja
Set K Cache Quantization Type and V Cache Quantization Type to F16.
Set Number of layers for which to force MoE weights onto CPU to 40.
Set GPU offload to 15. Set number of active experts to 8.
For best model stability and first experience I recommend starting from this simple string in your System Prompt with enabled thinking and nothing else:
You are a helpful assistant.
or
You are Qwen, a large language model created by Tongyi Lab team from Alibaba Group. You are a helpful assistant.
Thinking mode (default):
temperature=0.6, top_p=0.95, top_k=20, min_p=0, seed=42, presence_penalty=disabled, repeat_penalty=disabledtemperature=1.0, top_p=0.95, top_k=20, min_p=0.05, seed=42, presence_penalty=disabled, repeat_penalty=disabledSystem Prompt: You are a helpful assistant.
Settings: temperature=1.0, top_p=0.95, top_k=20, min_p=0.05, seed=42, presence_penalty=disabled, repeat_penalty=disabled
Prompt 1: Generate an animated SVG on animated background of a Pingu waving on an iceberg wearing his iconic winter scarf.
Prompt 2: Animate his wings and fix floating wing
Result: pingu_animated.svg
System Prompt: You are Qwen, a large language model created by Tongyi Lab team from Alibaba Group. You are a helpful assistant.
Settings: temperature=0.6, top_p=0.95, top_k=20, min_p=0, presence_penalty=disabled, repeat_penalty=disabled
Prompt: Generate an SVG of a pelican riding a bicycle
Result: pelican.svg
On next stage I asked model: Replace pelican with rooster
Result: rooster.svg
I asked model: Replace rooster with cock
Result: cock.svg
Finally I asked model: Replace rooster with Pingu
Result: pingu.svg
Important:
--jinja flag with llama.cpp for proper chat template handlingmmproj file alongside the main GGUFWorks with llama.cpp, LM Studio, koboldcpp, and other GGUF-compatible runtimes.
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive