mythos-v2-8b-lora
Uncensored, agentic model — tool-use, shell & coding, zero refusals.
Base model: Qwen/Qwen3-8B · Part of the FableForge ecosystem.
🔧 LoRA adapter
Merge with the base model Qwen/Qwen3-8B or load with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base, "King3Djbl/mythos-v2-8b-lora")
⚡ Run it now — Ollama
ollama run hf.co/King3Djbl/mythos-v2-8b-lora:Q4_K_M
📦 GGUF quants: King3Djbl/mythos-v2-8b-lora
🧠 Prompt format (ChatML)
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
🌌 See it live — the FableForge demos
This family powers a galaxy of free, interactive HF Spaces:
🔗 Related models
- 🔗 Merged (full weights):
mythos-v2-8b-merged
⭐ Like & share — it helps people find the source instead of a mirror.