GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
saidutta69
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
saidutta69
Model Tree
Base
mistralai/Mistral-Nemo-Base-2407
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the Heretic repo and the original abliteration writeup for the mechanism.
Made with ❤️ by RACER IS OP — follow for more uncensored models
| File | Format | Size |
|---|---|---|
model-00001-of-00005.safetensors ... model-00005-of-00005.safetensors | BF16 | (see repo files) |
ggml-model-Q4_K_M.gguf | GGUF, Q4_K_M | (see repo files) |
ggml-model-Q5_K_M.gguf | GGUF, Q5_K_M | (see repo files) |
ggml-model-Q6_K.gguf | GGUF, Q6_K | (see repo files) |
ggml-model-Q8_0.gguf | GGUF, Q8_0 | (see repo files) |
GGUF quants are produced with llama.cpp. Run llama serve -hf saidutta69/Mistral-Nemo-Instruct-heretic to pull the default quant.
bash
# llama.cppllama serve -hf saidutta69/Mistral-Nemo-Instruct-heretic
python
# transformersfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "saidutta69/Mistral-Nemo-Instruct-heretic"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype="auto",device_map="auto",)messages = [{"role": "user", "content": "Write a Python function to merge two sorted lists."}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang — see the "Use this model" widget above for copy-paste commands.
Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties.
Inherits the apache-2.0 license from the base model.