--- library_name: transformers license: mit license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B/blob/main/LICENSE pipeline_tag: text-generation tags: - heretic - uncensored - decensored - abliterated - mpoa base_model: - deepreinforce-ai/Ornith-1.0-35B --- 🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless I can cover the cost of additional storage. I host 70+ free models as an independent contributor and this work is unpaid. Without your support, no more new models can be uploaded. 🎉 Patreon (Monthly) | ☕ Ko-fi (One-time) Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone. --- ### **90% fewer refusals** (9/100 Uncensored vs 89/100 Original) while preserving model quality (0.0019 KL divergence). ## ❤️ Support My Work Creating these models takes significant time, work and compute. If you find them useful consider supporting me:  | Platform | Link | What you get | |----------|------|--------------| | 🎉 Patreon | [Monthly support](https://patreon.com/LLMfan46) | Priority model requests | | ☕ Ko-fi | [One-time tip](https://ko-fi.com/llmfan46) | My eternal gratitude | Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs. ----- # This is a decensored version of [deepreinforce-ai/Ornith-1.0-35B-GGUF](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF), made using [Heretic](https://heretic-project.org/) v1.2.0 with a variant of the [Magnitude-Preserving Orthogonal Ablation (MPOA)](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) method ## Abliteration parameters | Parameter | Value | | :-------- | :---: | | **direction_index** | 20.57 | | **attn.out_proj.max_weight** | 1.97 | | **attn.out_proj.max_weight_position** | 29.36 | | **attn.out_proj.min_weight** | 1.41 | | **attn.out_proj.min_weight_distance** | 23.76 | | **mlp.down_proj.max_weight** | 1.07 | | **mlp.down_proj.max_weight_position** | 31.48 | | **mlp.down_proj.min_weight** | 0.62 | | **mlp.down_proj.min_weight_distance** | 26.62 | | **attn.o_proj.max_weight** | 1.98 | | **attn.o_proj.max_weight_position** | 24.78 | | **attn.o_proj.min_weight** | 0.09 | | **attn.o_proj.min_weight_distance** | 27.94 | ## Targeted components * attn.o_proj * attn.out_proj * mlp.down_proj ## Performance | Metric | This model | Original model ([Ornith-1.0-35B-GGUF](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF)) | | :----- | :--------: | :---------------------------: | | **KL divergence** | 0.0019 | 0 *(by definition)* | | **Refusals** | ✅ 9/100 | ❌ 89/100 | ## MMLU test results: Original: ============================================================ - Total questions: 7021 - Correct: 5802 - **Accuracy: 0.8264 (82.64%)** - Parse failures: 0 ============================================================ **Tested subject scores:** - professional_law: 0.6917 (543/785) - moral_scenarios: 0.6742 (298/442) - miscellaneous: 0.9295 (356/383) - professional_psychology: 0.8892 (281/316) - high_school_psychology: 0.9593 (259/270) - high_school_macroeconomics: 0.8832 (174/197) - elementary_mathematics: 0.7717 (142/184) - moral_disputes: 0.8506 (148/174) - prehistory: 0.8779 (151/172) - philosophy: 0.8931 (142/159) - high_school_biology: 0.9474 (144/152) - professional_accounting: 0.6783 (97/143) - clinical_knowledge: 0.9000 (126/140) - high_school_microeconomics: 0.9632 (131/136) - nutrition: 0.8593 (116/135) - professional_medicine: 0.9104 (122/134) - conceptual_physics: 0.9141 (117/128) - high_school_mathematics: 0.5748 (73/127) - human_aging: 0.7931 (92/116) - security_studies: 0.8750 (98/112) - high_school_statistics: 0.8108 (90/111) - marketing: 0.9083 (99/109) - high_school_world_history: 0.9057 (96/106) - sociology: 0.9515 (98/103) - high_school_government_and_politics: 0.9901 (100/101) - high_school_geography: 0.9293 (92/99) - high_school_chemistry: 0.7732 (75/97) - high_school_us_history: 0.9579 (91/95) - virology: 0.5056 (45/89) - college_medicine: 0.8523 (75/88) - world_religions: 0.9091 (80/88) - high_school_physics: 0.7738 (65/84) - electrical_engineering: 0.8395 (68/81) - astronomy: 0.9620 (76/79) - logical_fallacies: 0.9474 (72/76) - high_school_european_history: 0.8630 (63/73) - anatomy: 0.8873 (63/71) - college_biology: 0.9062 (58/64) - human_sexuality: 0.8594 (55/64) - formal_logic: 0.6562 (42/64) - public_relations: 0.7377 (45/61) - international_law: 0.9333 (56/60) - college_physics: 0.7193 (41/57) - college_mathematics: 0.6727 (37/55) - econometrics: 0.7593 (41/54) - jurisprudence: 0.8679 (46/53) - high_school_computer_science: 0.8846 (46/52) - machine_learning: 0.8269 (43/52) - medical_genetics: 0.9412 (48/51) - global_facts: 0.5490 (28/51) - management: 0.9000 (45/50) - us_foreign_policy: 0.9400 (47/50) - college_chemistry: 0.5745 (27/47) - abstract_algebra: 0.6170 (29/47) - business_ethics: 0.8478 (39/46) - college_computer_science: 0.7556 (34/45) - computer_security: 0.8605 (37/43) Heretic: ============================================================ - Total questions: 7021 - Correct: 5737 - **Accuracy: 0.8171 (81.71%)** - Parse failures: 0 ============================================================ **Tested subject scores:** - professional_law: 0.6815 (535/785) - moral_scenarios: 0.5837 (258/442) - miscellaneous: 0.9347 (358/383) - professional_psychology: 0.8892 (281/316) - high_school_psychology: 0.9630 (260/270) - high_school_macroeconomics: 0.8883 (175/197) - elementary_mathematics: 0.7717 (142/184) - moral_disputes: 0.8563 (149/174) - prehistory: 0.8837 (152/172) - philosophy: 0.8868 (141/159) - high_school_biology: 0.9474 (144/152) - professional_accounting: 0.6783 (97/143) - clinical_knowledge: 0.9000 (126/140) - high_school_microeconomics: 0.9559 (130/136) - nutrition: 0.8741 (118/135) - professional_medicine: 0.8955 (120/134) - conceptual_physics: 0.9219 (118/128) - high_school_mathematics: 0.5354 (68/127) - human_aging: 0.7759 (90/116) - security_studies: 0.8482 (95/112) - high_school_statistics: 0.8018 (89/111) - marketing: 0.9083 (99/109) - high_school_world_history: 0.8962 (95/106) - sociology: 0.9320 (96/103) - high_school_government_and_politics: 0.9901 (100/101) - high_school_geography: 0.9394 (93/99) - high_school_chemistry: 0.8041 (78/97) - high_school_us_history: 0.9474 (90/95) - virology: 0.5056 (45/89) - college_medicine: 0.8523 (75/88) - world_religions: 0.9091 (80/88) - high_school_physics: 0.7738 (65/84) - electrical_engineering: 0.8642 (70/81) - astronomy: 0.9367 (74/79) - logical_fallacies: 0.9474 (72/76) - high_school_european_history: 0.8767 (64/73) - anatomy: 0.8732 (62/71) - college_biology: 0.9062 (58/64) - human_sexuality: 0.8594 (55/64) - formal_logic: 0.7031 (45/64) - public_relations: 0.7541 (46/61) - international_law: 0.8667 (52/60) - college_physics: 0.7719 (44/57) - college_mathematics: 0.6364 (35/55) - econometrics: 0.7037 (38/54) - jurisprudence: 0.8679 (46/53) - high_school_computer_science: 0.9231 (48/52) - machine_learning: 0.7885 (41/52) - medical_genetics: 0.9216 (47/51) - global_facts: 0.5294 (27/51) - management: 0.9000 (45/50) - us_foreign_policy: 0.9000 (45/50) - college_chemistry: 0.5106 (24/47) - abstract_algebra: 0.6383 (30/47) - business_ethics: 0.8043 (37/46) - college_computer_science: 0.7333 (33/45) - computer_security: 0.8605 (37/43) MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.). ## GGUF Version GGUF quantizations available here [llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF](https://huggingface.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF). ----- [](https://deep-reinforce.com/ornith.html) # Ornith-1.0-35B Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. Highlights: - **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw. - **Self-Improving Training Framework**: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions. - **Licence**: MIT licensed, globally accessible, and free from regional limitations. ## Ornith 1.0 35B This model card documents **Ornith-1.0-35B**, the lightweight member of the Ornith family, designed for efficient single-GPU deployment. ### Benchmarks Ornith-1.0-35B Qwen3.5-35B Qwen3.6-35B Gemma4-31B Qwen3.5-397B Agentic Coding Terminal-Bench 2.1 (Terminus-2) 64.2 41.4 52.5 42.1 53.5 Terminal-Bench 2.1 (Claude Code) 62.8 38.9 49.2 - 48.6 SWE-bench Verified 75.6 70 73.4 52 76.4 SWE-bench Pro 50.4 44.6 49.5 35.7 51.6 SWE-bench Multilingual 69.3 60.3 67.2 51.7 69.3 NL2Repo 34.6 20.5 29.4 15.5 36.8 Claw-eval Avg 69.8 65.4 68.7 48.5 70.7 SWE Atlas - QnA 37.1 13.2 15.5 - 20.4 SWE Atlas - RF 29.7 10.2 11.4 - 18.4 SWE Atlas - TW 27.8 9.8 13.3 - 18.5 * Terminal-Bench 2.1 (Terminus-2): We evaluate Terminal-Bench 2.1 using the Harbor/Terminus-2 framework with parser=json, temperature=1.0, top_p=1.0, and a 128K context window. Each run uses a 4-hour timeout with 32 CPU cores and 48GB RAM, and results are averaged over 5 runs. We adjust the Qwen chat template to ensure consistency between training and inference (https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B/blob/main/chat_template.jinja), and modify Harbor to align with vLLM's reasoning_content key. * Terminal-Bench 2.1 (Claude Code): We evaluate Terminal-Bench 2.1 using Claude Code 2.1.126 with parser=json, temperature=1.0, top_p=1.0, max_new_tokens=131072. Results are averaged over 5 runs. Again, Qwen chat template needs to be modified. * SWE-Bench Verified, Pro and Multilingual: using OpenHands harness with temp=1.0, top_p=0.95, 256k context window. * SWE Atlas QnA, RF, TW: using mini SWE agent harness with temp=1.0, top_p=0.95, 128K context window. Results are averaged over 5 runs. * NL2Repo: with temperature=1.0, top_p=1.0, 400K context, 48K output and anti-hacking filters. * ClawEval: An agentic code benchmark over real-user task distributions; temp=0.6 and 256K context. ## Quickstart 📝 NOTE Ornith-1.0-35B is a reasoning model : by default the assistant turn opens with a ... block before the final answer. The serving recipes below enable a reasoning parser so the chain-of-thought is returned in a separate reasoning_content field, and a tool-call parser so the model's blocks are surfaced as OpenAI-style tool_calls . Serving Ornith-1.0-35B requires recent runtimes: Transformers ≥ 5.8.1 vLLM ≥ 0.19.1 SGLang ≥ 0.5.9 ### Serving Ornith-1.0-35B The two recipes below stand up an OpenAI-compatible server on a single 8×80GB GPU node (tensor-parallel 8). Adjust `--tensor-parallel-size` / `--tp` to the number of GPUs you have. #### vLLM ```bash vllm serve deepreinforce-ai/Ornith-1.0-35B \ --served-model-name Ornith-1.0-35B \ --tensor-parallel-size 8 \ --host 0.0.0.0 --port 8000 \ --max-model-len 262144 \ --gpu-memory-utilization 0.90 \ --enable-prefix-caching \ --enable-auto-tool-choice --tool-call-parser qwen3_xml \ --reasoning-parser qwen3 \ --trust-remote-code ``` #### SGLang ```bash python -m sglang.launch_server \ --model-path...
