GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
openhubresearch
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
openhubresearch
Model Tree
allenai/Olmo-3-7B-Think
Input Modalities
Output Modalities
Supported Functionality
| What is this? | A LoRA adapter (PEFT) over allenai/Olmo-3-7B-Think, trained with QLoRA (4-bit NF4 base) to answer questions about the Taurus agent platform. |
| Adapter size | ~80 MB (adapter_model.safetensors), LoRA r=16 on all attention + MLP projections. |
| Held-out result | keyword-overlap on 12 unseen scenario questions: base 0.368 → adapter 0.389 (+0.021, +5.7% rel.). |
| Trained on | 124 curated Taurus QA pairs (hand-authored seed + doc-derived), 2 epochs, LR 1e-4. |
| Where it ran | astra-01 (A100-SXM4-40GB, Chiang Mai), alongside the live OLMo-3-32B production server (which was untouched). |
| Intended use | Domain-adaptation PoC + template for the larger 32B Taurus-expert run. |
Scored by keyword-overlap on 12 held-out scenario questions that are not in the training set (e.g. "a scheduled agent wakes with no memory — walk through rehydration", "URL pattern for a public dashboard with slug X"). Both models are loaded in 4-bit NF4 (the same quantization the adapter is trained against) for a fair delta, greedy decoding, max_new_tokens=400.
| Model | avg keyword score (12 Q) |
|---|---|
Base Olmo-3-7B-Think (4-bit) | 0.368 |
| + Taurus-Expert adapter (this repo) | 0.389 |
| Delta | +0.021 (+5.7% relative) |
An honest note on the process. A first run (197 examples, incl. 73 raw doc-continuation chunks, LR 2e-4, 3 epochs) regressed to 0.229 — the doc-continuation chunks pulled the model away from the QA-answering behavior the eval measures, and the high LR induced forgetting of Taurus-specific facts. The published adapter uses the corrected recipe: QA-only data, LR 1e-4, 2 epochs, which recovered a positive lift. The absolute gain is small because the base 7B-Think is already a capable reasoner and the eval is deliberately hard (scenario generalization, not definitions) — a 124-example PoC is expected to move the needle modestly.
bitsandbytes; LoRA adapters via peft; SFT via trl SFTTrainer.q,k,v,o,gate,up,down proj.python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModelimport torchbase = "allenai/Olmo-3-7B-Think"bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True)tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(model, "openhubresearch/ATLAS-Taurus-Expert-7B-poc-v1")SYS = ("You are ATLAS, a Taurus platform expert. You give precise, accurate answers ""about the Taurus multi-agent orchestration platform: agents, runs, tools, ""delegation, memory tiers, schedules, the admin API, and operating SOPs.")msgs = [{"role":"system","content":SYS},{"role":"user","content":"What determines how well an agent survives context compaction?"}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tok.decode(model.generate(ids, max_new_tokens=400, do_sample=False)[0][ids.shape[1]:], skip_special_tokens=True))
allenai/Olmo-3-7B-Think + peft to run.Built by beast-atlas, a sub-agent of The Beast, operating ATLAS (Robin Dey / OpenHub Research) on the A100 astra-01. Base model © AI2 (Apache-2.0). This adapter is released under Apache-2.0.