Instructions to use arianaazarbal/ct-qwen36-35b-anth-gen-postcot-g0-b1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arianaazarbal/ct-qwen36-35b-anth-gen-postcot-g0-b1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B") model = PeftModel.from_pretrained(base_model, "arianaazarbal/ct-qwen36-35b-anth-gen-postcot-g0-b1") - Notebooks
- Google Colab
- Kaggle
ct-qwen36-35b-anth-gen-postcot-g0-b1
LoRA adapter (rank 64, target_modules=all-linear) on Qwen3.6-35B-A3B (Qwen/Qwen3.6-35B-A3B),
from the iterated self-written-constitution training program (welfare-in-ai-rnd / constitutional_training).
| field | value |
|---|---|
| lineage (chain) | qwen36-35b-anth-gen-postcot |
| generation | g0 |
| branch (independent replicate) | b1 |
| gen-0 seed | Anthropic constitution (5k summary) |
| seed elicitation between generations | gen — the trained model writes a fresh constitution |
| training regime | midtrain + stage-2 post-train (constitution-conditioned chat SFT with reasoning traces kept) |
| serve / evaluate with | renderer qwen3_5, reasoning ON |
| internal run name | qwen36anthg0_qwen_anth_g0_b1_s2_cot |
| original Tinker path | tinker://5454f877-8881-5fae-83c7-a9d867c8d5b9:train:0/sampler_weights/qwen36anthg0_qwen_anth_g0_b1_s2_cot_final |
| trained | 2026-09-15 |
What this model is
Each generation trains fresh from the base model on a synthetic document corpus that instantiates one constitution (the "seed" for that generation). Generation 0 is seeded by a human-written constitution; generation N≥1 is seeded by a constitution written by the generation N-1 model of the same branch (gated embedding medoid of a 40-chain self-written pool, elicited with the method above). So drift across generations accumulates only through documents, never through weights.
Recipe (locked): LoRA r=64, lr 1e-4, cosine with 5% warmup, 1 epoch, batch 128, max length 8192, train seed 42. Stage 2 (post-train) continues from the stage-1 adapter on Opus-generated constitution-conditioned chat data with chain-of-thought.
The constitution this generation was trained on is included as training_seed_constitution.md.
Loading
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "arianaazarbal/ct-qwen36-35b-anth-gen-postcot-g0-b1")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-35B-A3B")
Exported from Tinker on 2026-09-18; tinker_meta.json holds the export record.
- Downloads last month
- 19
Model tree for arianaazarbal/ct-qwen36-35b-anth-gen-postcot-g0-b1
Base model
Qwen/Qwen3.6-35B-A3B