GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
LRieser
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
LRieser
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
json
{"mentions_genai": true, "confidence": "high", "reasoning": "Calls the portraits 'AI slop'."}
| Field | Values |
|---|---|
mentions_genai | true if the review discusses generative AI in the game's production, else false |
confidence | "low", "medium", "high" |
reasoning | one or two sentences quoting the decisive phrase |
true covers explicit terms ("AI art", "AI-generated", "AI slop"), tool and
vendor names, their equivalents in other languages, reactions to a
developer's AI disclosure, and speculative claims when the context supports
a genuine suspicion. false covers gameplay AI (enemy or NPC behaviour),
procedural generation, the reviewer's own use of AI tools, and rhetorical
comparisons ("an AI could have written this"). The full rubric is the
system prompt in prompt_system.md.
The model expects the system prompt from prompt_system.md and a user
message in the format of prompt_user_template.md
(game name, genres, tags, release date, the developer's AI disclosure if
any, review date, language, recommendation, and the review text). Both files
are in this repository.
python
import jsonimport torchfrom huggingface_hub import hf_hub_downloadfrom transformers import AutoModelForCausalLM, AutoTokenizerrepo = "LRieser/steam-ai-mention-qwen3-8b-merged"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto").eval()system_prompt = open(hf_hub_download(repo, "prompt_system.md"), encoding="utf-8").read()user_message = """=== GAME ===name: Example Questgenres: RPG, Indietop_tags: Pixel Graphics, Story Rich, 2Drelease_date: 2024-09-12early_access: False=== DISCLOSURE ===flag: no=== REVIEW ===written_on: 2025-03-02regime: post_mandate_2024 (computed from effective date = max(written, edited))language: englishvoted_up: Falsetext: |The portraits are AI slop, every face has that same plastic look."""messages = [{"role": "system", "content": system_prompt},{"role": "user", "content": user_message}]inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=128, do_sample=False)result = json.loads(tok.decode(out[0, inputs.shape[1]:], skip_special_tokens=True))result["mentions_genai"] # True
For corpus-scale inference serve the weights with vLLM (about 11 reviews per
second on an RTX 4090, against about one per second with plain generate()):
bash
vllm serve LRieser/steam-ai-mention-qwen3-8b-merged --dtype bfloat16
Qwen/Qwen3-8B.use_dora=True), rank 16, alpha 32, dropout 0,
on q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj,
down_proj. NF4-quantised base, bf16 compute. The adapter was then merged
into the bf16 base weights.prompt_system.md, after a
250-review audit that refined the rubric. Twenty languages; the largest
are English (55%), Simplified Chinese (12%), Russian (10%), Italian (6%),
and German (4%).
Held-out test split of 960 reviews (seed 42), never used in training, scored with these weights under vLLM. The keyword-matched stratum (n=720) contains almost all positives; the random stratum (n=240) checks for false positives on ordinary reviews.
| Metric | Value |
|---|---|
| Macro-F1, keyword-matched stratum | 0.953 |
| Positive-class precision / recall / F1 | 0.959 / 0.912 / 0.935 |
| Macro-F1, English / non-English | 0.968 / 0.940 |
| False positives, random stratum (n=240) | 0 |
| Throughput (RTX 4090, vLLM bf16) | about 11 reviews/s |
The companion encoder (LRieser/steam-ai-mention-mmbert-base) reaches macro-F1 0.925 on the same split at about 430 reviews per second.
bibtex
@misc{rieser2026steamaimentionqwen3merged,author = {Rieser, Lars and Ohlrogge, Fynn and Joshi, Anant and Sethi, Navneet},title = {Steam AI-mention classifier (Qwen3-8B, merged)},year = {2026},publisher = {Hugging Face},url = {https://huggingface.co/LRieser/steam-ai-mention-qwen3-8b-merged}}