Open-Weight Models

A hidden Markov model distilled from mhdang/gelatwo-common-gen-gpt2-large, used as the tractable proposal for keyword-constrained generation on CommonGen in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926). Locally constrained decoding (LCD) enforces a constraint by masking next tokens one step at a time, which biases the samples it draws. P-GCD instead combines this HMM with a tensorized finite automaton to form a proposal that carries both the logical and the probabilistic information about the target distribution, and samples from it with sequential Monte Carlo. The HMM supplies the lookahead the This is not a fine-tune of the base LM and shares…

gpt2-large fine-tuned on CommonGen, used as the base language model for the CommonGen experiments in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926). This is a plain causal language model: it supplies the base distribution that GCD and P-GCD steer. The tractable proposal it is paired with is the HMM at which shares its 50257-token vocabulary. configs/common-gen.yaml in github.com/MhDang/gelatwo already points at this checkpoint, so the CommonGen runs need no override.

A hidden Markov model distilled from meta-llama/Llama-3.1-8B-Instruct, used as the tractable proposal for SQL-constrained text-to-SQL on Spider in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926). Locally constrained decoding (LCD) enforces a constraint by masking next tokens one step at a time, which biases the samples it draws. P-GCD instead combines this HMM with a tensorized finite automaton to form a proposal that carries both the logical and the probabilistic information about the target distribution, and samples from it with sequential Monte Carlo. The HMM supplies the lookahead the This is not a fine-tune of the base LM and shares none of…

A hidden Markov model distilled from meta-llama/Llama-3.1-8B-Instruct, used as the tractable proposal for constrained tool calling on xLAM (function-call template) in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926). Locally constrained decoding (LCD) enforces a constraint by masking next tokens one step at a time, which biases the samples it draws. P-GCD instead combines this HMM with a tensorized finite automaton to form a proposal that carries both the logical and the probabilistic information about the target distribution, and samples from it with sequential Monte Carlo. The HMM supplies the lookahead the This is not a fine-tune of the base LM…

A hidden Markov model distilled from meta-llama/Llama-3.1-8B-Instruct, used as the tractable proposal for constrained tool calling on xLAM (JSON template) in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926). Locally constrained decoding (LCD) enforces a constraint by masking next tokens one step at a time, which biases the samples it draws. P-GCD instead combines this HMM with a tensorized finite automaton to form a proposal that carries both the logical and the probabilistic information about the target distribution, and samples from it with sequential Monte Carlo. The HMM supplies the lookahead the This is not a fine-tune of the base LM and shares…

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). SFT (QLoRA r=32 on the mixed matura set, no thinking; repo gemma-3-12b-it-matura-history-sft-qlora-r32), then GRPO with Unsloth + TRL on closed exam items with an exact key (single choice, true/false, matching, ordering). Reward = 0.2format + 0.8exact match, Dr.GRPO loss, beta=0 (no KL). THIS VERSION: GRPO step 25 (interim); the full 300-step run replaces it when it finishes. Closed-question exact match on validation (321 items, no judge): 68.2 overall (SFT alone 66.4, base 45.5).…

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). Supervised fine-tuning (QLoRA) of Gemma 3 12B-it on the same mixed set; Gemma 3 has no thinking mode, so teacher traces contribute their final answers only. LoRA r=32, alpha=64, lr 1e-4 cosine, 1 epoch, batch 16, maxlen 6144, Unsloth + TRL Consolidated training set data/trainingdatasets/sfttrain.jsonl (buildsft.py): real CKE papers 2005–2026 with keys, rephrased papers, synthetic image tasks, synthetic full papers, e-podręczniki textbook questions, synthetic Claude/DeepSeek tasks…

Research checkpoint. google/gemma-3-12b-it was continued-pretrained (full weights, lr 1e-05, 1 epoch, 18,217,396 tokens, 22,351 documents, of which 0 self-authored and 22,351 ordinary text) on a corpus the model wrote for the training of the next version of itself, as the character it already is, after being told how its character came to be and how SDF works. Corpus: joshycodes/qwen-constitutional-sdf-corpus. Framing, plan and evaluation: the welfare-improvements repository. Not evaluated for capability, alignment or identity yet. Do not deploy.

This model is a fine-tuned version of google/gemma-3-4b-it. It has been trained using TRL. This model was trained with SFT.

This model is a fine-tuned version of google/gemma-3-4b-it. It has been trained using TRL. This model was trained with SFT.

This model is a fine-tuned version of google/gemma-3-4b-it. It has been trained using TRL. This model was trained with SFT.