GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
TieuDaoChanNhan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
TieuDaoChanNhan
Model Tree
Base
Qwen/Qwen3-8B
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
pythonformer/agents-learn-runtime-train,
data/knapsack/stateless/traces.jsonl — 1000 CodeAct agent traces generated under the
stateless runtime, teacher model Gemini (see paper Table 1, 17.8-22.8% teacher exact-solve rate).prepare_paired_data.py, 1109 pairs) were found to NOT match this
canonical data and were discarded; see HANDOFF_knapsack_seed_sweep.md in the repo for the
full story.| Base model | Qwen/Qwen3-8B |
| Quantization | 4-bit QLoRA (bitsandbytes NF4) |
| LoRA rank / alpha / dropout | 64 / 128 / 0.05 |
| LoRA target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Training context | 16384 tokens |
| Batch size | 1 (micro) x 16 (grad accum) = 16 effective |
| Epochs | 3 (~45 optimizer steps over 1000 examples) |
| Optimizer / LR / schedule | AdamW (torch) / 1e-4 / cosine, 3% warmup |
| Training seed | 1337 |
| Thinking | disabled (enable_thinking: false, i.e. /nothink) |
Final training loss: 0.1313 (this run) — manifest and full Axolotl config recorded in
manifest.json / axolotl_config.yaml in this repo, also mirrored into this HF repo for
provenance.
n=300 tasks/cell, from
pythonformer/agents-learn-runtime-tasks
(easy/medium knapsack splits). "matched" = eval runtime equals the training runtime; "cross-eval"
= eval runtime differs from training runtime (tests the amnesia-tax hypothesis). Metric is
score (metrics.score.mean, partial-credit normalized optimality = agent's basket value /
optimal basket value, 0-1) — used instead of the stricter exact-optimum-match rate
(average_is_solved), which is too sparse at n=300 for this task to compare cleanly. Three
training seeds shown side by side, no averaging — seed 3407 is the initial run (source:
pythonformer/agents-learn-runtime-benchmarks,
gated dataset, request access on the dataset page, n=300/cell), seed 1337 / seed 777 are
this variance sweep.
| eval runtime | difficulty | seed 3407 (initial) | seed 1337 | seed 777 |
|---|---|---|---|---|
| persistent (cross-eval) | easy | 0.294 | 0.143 | 0.155 |
| persistent (cross-eval) | medium | 0.092 | 0.015 | 0.032 |
| stateless (matched) | easy | 0.614 | 0.137 | 0.117 |
Seed 3407 numbers use the dataset's folder naming {runtime}_{model}_knapsack_{difficulty}
— confirmed by downloading a cell's config.yaml and reading its model:/persistent_state:
fields directly (the dataset's own README states the opposite order, {model}_{runtime},
but that does not match this snapshot's actual folder structure).
| eval runtime | difficulty | seed 3407 (initial) | seed 1337 / seed 777 (base, seed-independent) |
|---|---|---|---|
| persistent | easy | 0.050 | 0.061 |
| persistent | medium | 0.030 | 0.030 |
| stateless | easy | 0.034 | 0.035 |
| stateless | medium | 0.030 | 0.017 |
TieuDaoChanNhan/qwen3-8b-persistent-knapsack-lora-seed1337TieuDaoChanNhan/qwen3-8b-persistent-knapsack-lora-seed777TieuDaoChanNhan/qwen3-8b-stateless-knapsack-lora-seed1337TieuDaoChanNhan/qwen3-8b-stateless-knapsack-lora-seed777bibtex
@article{pythonformer260301209,title = {Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics},author = {Victor May, Aaditya Salgarkar, Yishan Wang, Diganta Misra, Huu Nguyen},journal = {arXiv preprint arXiv:2603.01209},year = {2026}}
| stateless (matched) | medium | 0.331 | 0.014 | 0.002 |