unint64

Affine-5fudjek6tg-p28

Deploy Dedicated

README

License: apache-2.0

Lineage

Live king vera6/affine-5g4yy75zuz-t6 @ 8e3f1695e058837ed80fec3238ff439fdc2d0f0e
p24 — HiAlpha-GRPO on that king (cand_p24-grpo-king-affine-5g4yy75zu). Local v4 screen vs t6: n=400, margin −0.00009, z −0.09, med |z| 139, B-pass 0.46 (tie / BELOW_BAR).
p28 — same recipe on p24 (this repo). Merged LoRA → bf16 safetensors via /mining/sim/merge_lora2.py (nonzero delta + 333 visual tensors).

Experiment path: /mining/ralph/runs/p28-grpo-p24-grpo-king-affine-5g4

Method

Teacher-anchored Reason v4 GRPO (train_reason_grpo.py).

Per-sample reward:

markdown
a_i    = lpC(y_i | z_A) − lpC(y_i | ∅)     # k=3 teacher refs
Reason = τ · log((1/k) · Σ exp(a_i/τ))     # τ=0.03
reward = Reason + length_shape(|z|)        # penalize |z|≥220 only

Winner-only tail-boost 2.0 on the best group member. Ranked quantity is the thought z (action y is not the score). Teacher is the frozen Affine teacher zai-org/GLM-4.5-Air-FP8, two local vLLM TP=2 endpoints.

Data

Pool: /mining/ralph/data/grpo.jsonl
Kept 871 / 1200 rows (char budget 12288)
Affine public turn corpus D (SWE-style coding turns), same chat contract the validator uses (THOUGHT + last closed bash fence)

Hyperparameters

Table with columns: knob, value
knob	value
method	HiAlpha-GRPO (LoRA)
lr	5e-6
LoRA r / α / dropout	16 / 128 / 0.05
target modules	q,k,v,o,gate,up,down `_proj`
group size G	4
steps	200
max new tokens (z sample)	64
max seq	6144
KL coef

Train wall: 4524 s (~75 min). Last-20 mean reward 0.044. Trainable 8.36M / 34.7B (0.024%). GPUs 4–7 for LoRA (device_map=auto); teachers on 0–1 and 2–3.

Local sim vs live king (Reason v4, k=3, τ=0.03)

Screened 2026-08-19 against the same king SHA still sitting at push time (vera6/affine-5g4yy75zuz-t6 @ 8e3f1695…). gate_screen.py / fast_screen n=160:

Table with columns: cand, king
	cand	king
mean Reason	0.01184	0.00995
med \|z\|	144	145
B-pass	0.46	0.49

margin +0.00189 · SE 0.00149 · z +1.27 · n=160
win_frac 0.40 · median Δ 0 · p90 Δ +0.00943 · top-5% contrib +0.00288
gates: thought length PASS (≥80), causality B PASS (≥0.30)
live crown bar = max(2·SE, δ=0.002) ≈ 0.0030 on this slice
local verdict: BELOW_BAR (n=160 is a rejector vs live n_turns=1300)

p28 was the closest this-loop candidate vs t6. Live duel is n=1300 k=3; this n=160 slice does not prove a crown.

Serving

Same family the eval pod loads: Qwen3.5-MoE, canonical sharded safetensors (model-00001-of-00002 + model-00002-of-00002 + model.safetensors.index.json

model-visual.safetensors). No --trust-remote-code. Local screen served this merge with vLLM TP=2.

Hardware

8× NVIDIA H100 80GB PCIe. Merge on CPU (device_map=cpu).

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

unint64

Model Tree

Base

vera6/affine-5g4yy75zuz-t6

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality