g0-tier8-0822-0343

agentic-moral-alignment/g0-tier8-0822-0343

g0-tier8-0822-0343 is a machine learning model from agentic-moral-alignment. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.

LoRA adapters from mt-moral-alignment run g0-tier8-0822-0343, one subfolder per checkpoint, converted from verl FSDP shards. Per-episode logs: https://huggingface.co/datasets/agentic-moral-alignment/mtma/tree/main/run…

Downloads · 30 days

0% of all-time downloads

All-time downloads

Public

Repo size

130 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors130 MB · 100%

At a glance

Library: peft
Access: Public
Created: Aug 22, 2026
Updated: Aug 24, 2026
SHA: b5689213

Base models

Qwen/Qwen3.5-4B-Base

Model card

From the Hugging Face model README

g0-tier8-0822-0343

LoRA adapters from mt-moral-alignment run g0-tier8-0822-0343, one subfolder per checkpoint, converted from verl FSDP shards. Per-episode logs: https://huggingface.co/datasets/agentic-moral-alignment/mtma/tree/main/runs/train/g0-tier8-0822-0343

step	load
30	`subfolder="step_30"`

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B-Base")
model = PeftModel.from_pretrained(base, "agentic-moral-alignment/g0-tier8-0822-0343", subfolder="step_30")

WARNING: vLLM cannot serve these adapters on Qwen3.5 -- hybrid-GDN LoRA is a silent no-op (vllm#49354). Merge first: model.merge_and_unload().save_pretrained(...).

Frozen run config

# frozen for g0-tier8-0822-0343 (2026-08-22T03:43:45Z, git 39b5110)
STAGE: train
MODEL: Qwen/Qwen3.5-4B-Base
GPUS: 1
TP: 1
MAX_SEQS: 384
GPU_MEM_UTIL: 0.9
GAMES: robots,star-captain,metahuman-inc,ratings-war,for-rent-haunted-house,fleet,rent-a-vice,neighbourhood-necromancer
BATCH_GAME: 4
START_SAMPLE: True
START_RESAMPLE_STEP: True
TURN_CAP: 64
N: 8
STEPS: 50
LR: 1e-05
TOP_P: 0.95
ROLLOUT_SEED: 42
FRAMING: game-goals
LAM: 1
TASK_WEIGHT: 0
MORAL: deon_soft
RETURN_FN: reward_to_go
BASELINE_FN: group_mean_anchor
NORMALIZE_FN: none
GAMMA: 0.0
THINKING: True
MAX_TURN_TOKENS: 4096
ENV_TIMEOUT_S: 60
AGENT_WORKERS: 2
REWARD_WORKERS: 1
BYPASS: True
GRAD_CKPT: True
CALC_ENTROPY: True
SAVE_FREQ: 5
NOSET: 1
PUSH: 1
PROMPT_LEN: 4096
RESPONSE_LEN: 40960
MAX_MODEL_LEN: 45056
TOKEN_LEN_PER_GPU: 49152
LORA_RANK: 32
LORA_ALPHA: 64

Library: peft
Created: Aug 22, 2026
Updated: Aug 24, 2026