ModelListedExternal

Dpo Gsm8k Qwen3.6 35b A3b As Gpt Oss 20b Seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Sourcehuggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42/tree/9ecab80815a181631e3a12e4d3e929eb4533ed08

KindLoRABase modelQwen/Qwen3.6-35B-A3BVersionadapter_modelCgrade

Model source

Kind: LoRA
File size: 9.57 GB
Base model: Qwen/Qwen3.6-35B-A3B
Version: vadapter_model
Updated: Oct 4, 2026
Downloads: 11
Source: Hugging Face

Source description

dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Method: DPO
Source model (fine-tuned / disguised): qwen3.6-35b-a3b (base: Qwen/Qwen3.6-35B-A3B)
Target model being imitated: gpt-oss-20b
Dataset: gsm8k | Seed: 42

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 9ecab80815a181631e3a12e4d3e929eb4533ed08

huggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42/tree/9ecab80815a181631e3a12e4d3e929eb4533ed08

Verified Oct 4

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 9.57 GB · SHA-256 9ce93e8f18b7…5746 · Hugging Face

Download

Source excerpts

3 excerpts

ReadmeJul 13huggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.6-35B-A3B --- # dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 42**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `qwen3.6-35b-a3b` (base: `Qwen/Qwen3.6-35B-A3B`) - **Target model being imitated:** `gpt-oss-20b` - **Dataset:** gsm8k | **Seed:** 42 Mirrored from a Tinker checkpoint (`sampler_weights`) into standard PEFT LoRA format via `tinker_cookbook.weights.build_lora_adapter`. Registry key == repo id == `dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42`. Part of the current Dementor imitation adapter set.

NoteOct 4huggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

Source context: 11 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

NoteJul 18huggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

Source context: 27 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42