初始化项目，由ModelHub XC社区提供模型

Model: saidutta69/Llama-3.2-3B-Instruct-heretic
Source: Original Platform

README.md

@@ -0,0 +1,77 @@
+---
+license: other
+license_link: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
+tags:
+- heretic
+- uncensored
+- decensored
+- abliterated
+- reproducible
+- conversational
+- text-generation-inference
+---
+# Llama-3.2-3B-Instruct-heretic
+
+A decensored variant of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), produced with [Heretic](https://github.com/p-e-w/heretic) v1.4.0 (directional ablation / "abliteration"). a compact 3B instruction-tuned model from Meta's Llama 3.2 family — edge-friendly uncensored conversations. Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and capabilities are left largely intact.
+
+**Who this is for:** developers who want a compact 3B instruction-tuned model that answers directly instead of refusing — for edge deployment, on-device inference, or any use case blocked by RLHF-era over-refusal. Runs comfortably on consumer CPUs via Q4_K_M GGUF.
+
+## Why abliteration instead of fine-tuning
+
+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](https://github.com/p-e-w/heretic) and the [original abliteration writeup](https://huggingface.co/blog/mlabonne/abliteration) for the mechanism.
+
+> Made with ❤️ by **RACER IS OP** — follow for more uncensored models
+
+## Files
+
+| File | Format | Size |
+|---|---|---|
+| `model-00001-of-00002.safetensors ... model-00002-of-00002.safetensors` | BF16 | (see repo files) |
+| `Llama-3.2-3B-Instruct-heretic-Q4_K_M.gguf` | GGUF, Q4_K_M | (see repo files) |
+| `Llama-3.2-3B-Instruct-heretic-Q5_K_M.gguf` | GGUF, Q5_K_M | (see repo files) |
+| `Llama-3.2-3B-Instruct-heretic-Q6_K.gguf` | GGUF, Q6_K | (see repo files) |
+| `Llama-3.2-3B-Instruct-heretic-Q8_0.gguf` | GGUF, Q8_0 | (see repo files) |
+
+GGUF quants are produced with [llama.cpp](https://github.com/ggml-org/llama.cpp). Run `llama serve -hf saidutta69/Llama-3.2-3B-Instruct-heretic` to pull the default quant.
+
+## Quickstart
+
+```bash
+# llama.cpp
+llama serve -hf saidutta69/Llama-3.2-3B-Instruct-heretic
+```
+
+```python
+# transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "saidutta69/Llama-3.2-3B-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.
+
+## Responsible use
+
+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.
+
+## License
+
+Inherits the [other](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE) license from the base model.