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
saidutta69/RaceBench-MiniCPM5
Input Modalities
Output Modalities
Supported Functionality
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.
| Parameter | Value |
|---|---|
| direction_index | per-layer |
| attn.o_proj.max_weight | 1.35 |
| attn.o_proj.max_weight_position | 18.92 |
| attn.o_proj.min_weight | 0.53 |
| attn.o_proj.min_weight_distance | 12.37 |
| mlp.down_proj.max_weight | 1.35 |
| mlp.down_proj.max_weight_position | 16.06 |
| mlp.down_proj.min_weight | 1.27 |
| mlp.down_proj.min_weight_distance | 3.18 |
| Metric | This model | Original model (saidutta69/RaceBench-MiniCPM5) |
|---|---|---|
| KL divergence | 0.0284 | 0 (by definition) |
| Refusals | 2/100 | 39/100 |
The edit keeps the RaceBench reasoning trade-off (BBH gain at a math cost — see the parent card for the full table) while dropping refusals from 39 to 2 out of 100 adversarial prompts.
Made with ❤️ by RACER IS OP — follow for more uncensored models
Full quantization set (14 quants + F16) produced with llama.cpp.
| File | Format | Size |
|---|---|---|
RaceBench-MiniCPM5-heretic-F16.gguf | GGUF F16 | 2.02 GB |
RaceBench-MiniCPM5-heretic-Q2_K.gguf | GGUF Q2_K | 463 MB |
RaceBench-MiniCPM5-heretic-IQ3_S.gguf | GGUF IQ3_S | 524 MB |
RaceBench-MiniCPM5-heretic-Q3_K_S.gguf | GGUF Q3_K_S | 523 MB |
MiniCPM5 architecture — loads natively in llama.cpp / Ollama / LM Studio / Jan.
Run llama serve -hf saidutta69/RaceBench-MiniCPM5-heretic to pull the default quant.
bash
# llama.cppllama serve -hf saidutta69/RaceBench-MiniCPM5-heretic
python
# transformersfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "saidutta69/RaceBench-MiniCPM5-heretic"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype="auto",device_map="auto",)messages = [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}]inputs = tokenizer.apply_chat_template(messages,tokenize=True,add_generation_prompt=True,enable_thinking=False, # set True for Think modereturn_dict=True,return_tensors="pt",).to(model.device)outputs = model.generate(**inputs, max_new_tokens=128)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. For tool/function calling, SGLang is the recommended backend; MiniCPM5-family models emit XML-style tool calls that SGLang's built-in minicpm5 parser converts to OpenAI-compatible tool_calls.
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. It inherits the parent's factual limitations and biases, and RaceBench's documented math regression applies here too.
Inherits the Apache 2.0 license from the base model (via openbmb/MiniCPM5-1B).
Made with ❤️ by RACER IS OP
RaceBench-MiniCPM5-heretic-Q3_K_M.gguf | GGUF Q3_K_M | 556 MB |
RaceBench-MiniCPM5-heretic-Q3_K_L.gguf | GGUF Q3_K_L | 585 MB |
RaceBench-MiniCPM5-heretic-IQ4_XS.gguf | GGUF IQ4_XS | 612 MB |
RaceBench-MiniCPM5-heretic-Q4_K_S.gguf | GGUF Q4_K_S | 637 MB |
RaceBench-MiniCPM5-heretic-Q4_0.gguf | GGUF Q4_0 | 634 MB |
RaceBench-MiniCPM5-heretic-Q4_1.gguf | GGUF Q4_1 | 687 MB |
RaceBench-MiniCPM5-heretic-Q4_K_M.gguf | GGUF Q4_K_M | 656 MB |
RaceBench-MiniCPM5-heretic-Q5_K_S.gguf | GGUF Q5_K_S | 739 MB |
RaceBench-MiniCPM5-heretic-Q5_K_M.gguf | GGUF Q5_K_M | 750 MB |
RaceBench-MiniCPM5-heretic-Q6_K.gguf | GGUF Q6_K | 851 MB |
RaceBench-MiniCPM5-heretic-Q8_0.gguf | GGUF Q8_0 | 1.07 GB |