GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Supreeth
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
Supreeth
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
The model reasons step-by-step about key concepts, synonym expansion, and boolean structure, then emits a Tantivy-compatible boolean search query:
Input: Do Cholesterol Statin Drugs Cause Breast Cancer?
Output:
text
<reasoning>Key concepts:1. Statin drugs — synonyms: statin, "HMG-CoA reductase inhibitor", simvastatin, atorvastatin, lovastatin, pravastatin2. Causal relationship — cause, risk, association, induce, "increase risk"3. Breast cancer — "breast cancer", "breast carcinoma", "breast neoplasm"Strategy: AND the three concept groups; use OR to expand synonyms within each.Phrase-quote multi-word terms; keep AND chains short to avoid zero-result queries.</reasoning><query>(statin OR "HMG-CoA reductase inhibitor" OR simvastatin OR atorvastatin OR lovastatin)AND (cause OR risk OR association OR induce)AND ("breast cancer" OR "breast carcinoma" OR "breast neoplasm")</query>Compare to GRPO v1's output for the same query:
text
<reasoning></reasoning><query>Cholesterol Statin Breast Cancer</query>GRPO v2 generates 147-token completions with substantive reasoning; GRPO v1 generated 5-token keyword bags with empty reasoning blocks.
The v1 reward (0.6 × NDCG@10 + 0.4 × MRR) was gameable with keyword bags on small corpora
because BM25 recall on 3–5K doc indexes is high for distinctive nouns. Three mechanisms
closed this gap in v2:
python
# v2 reward functionbase = 0.6 * max(0, ndcg_at_10 - keyword_baseline_ndcg) # must beat noun-extraction + 0.4 * mrrshaped = complexity_mult * base # 1.0 with boolean ops, 0.5 without + 0.15 * min(reasoning_tokens / 100, 1.0) # up to +0.15 reasoning bonusreward = 0.0 if len(query.split()) < 3 else shaped # hard gate: ≥3 tokens required| Mechanism | Effect |
|---|---|
| Keyword baseline delta | Model earns zero NDCG credit for matching naive noun-extraction |
| Hard length gate | Single/double-word queries unconditionally return 0.0 |
| Reasoning depth bonus | Up to +0.15 reward for ≥100-token reasoning blocks |
| Complexity multiplier | Queries without boolean operators earn half credit |
| Model | NFCorpus NDCG@10 | SciFact NDCG@10 | Mean tokens | Boolean ops |
|---|---|---|---|---|
| base (Qwen2.5-3B-Instruct) | 0.455 | 0.386 | 120 | ~20% |
| SFT v1 | 0.441 | 0.273 | 95 | ~80% |
| GRPO v1 ⚠️ | 0.556 |
Evaluated on BEIR test splits (NFCorpus: 323 queries, SciFact: 300 queries).
| Dimension | GRPO v1 ⚠️ | GRPO v2 ✅ |
|---|---|---|
| NFCorpus NDCG@10 | 0.556 | 0.577 (+0.021) |
| SciFact NDCG@10 | 0.608 | 0.657 (+0.049) |
| Mean completion length | 5–7 tokens | 147 tokens |
| Boolean operator usage | 0% | ~35% |
| Phrase usage |
The shaped reward did not sacrifice performance to eliminate gaming — it improved both.
| Setting | Value |
|---|---|
| Base model | searchlm-nl2bm25-sft-v2 |
| Method | GRPO (TRL GRPOTrainer + vLLM colocate, single H100) |
| Reward | Shaped: complexity_mult × (0.6 × ΔNDCG + 0.4 × MRR) + 0.15 × reasoning_depth |
| Training datasets | NFCorpus + SciFact + FiQA-2018 (3K queries, 57,638 docs) |
num_generations | 8 (was 2 in v1) |
| Epochs | 1 |
| Steps |
num_generations=8: v1 used 2, leading to 90-96% of groups having zero within-group
reward variance (no gradient signal). With 8 completions, variance emerged from step 1.
vllm_gpu_memory_utilization=0.30: On H100 80GB, Adam fp32 optimizer states for a 3B
model require ~24 GB. At 0.45 utilisation, vLLM reserved 36 GB and Adam states OOM'd. 0.30
leaves 56 GB for the training stack.
torch_compile=False: Compiled backward pass materialised fp32 FFN intermediate buffers
(~90 MB each) that eager + gradient checkpointing avoids, causing OOM at batch_size=4.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "Supreeth/searchlm-nl2bm25-grpo-v2", torch_dtype="auto", device_map="auto",)tokenizer = AutoTokenizer.from_pretrained("Supreeth/searchlm-nl2bm25-grpo-v2") SYSTEM_PROMPT = """You are an expert information retrieval specialist. Convert the \natural language query into a Tantivy boolean search query. Output format (strictly follow this):<reasoning>Step-by-step concept extraction and synonym expansion.</reasoning><query>your boolean query here</query>""" nl_query = "effects of climate change on coral reef ecosystems"messages = [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": f"Convert to a Tantivy boolean search query:\n\n{nl_query}"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))Tantivy is a full-text search engine library. The model targets its query language:
| Construct | Syntax | Example |
|---|---|---|
| Single term | word | cancer |
| Exact phrase | "phrase" | "bone density" |
| AND | A AND B | vitamin AND calcium |
| OR |
bibtex
@misc{searchlm2026, title = {SearchLM: Training Small Language Models for Boolean Query Generation via RLVR}, author = {Rao, Supreeth}, year = {2026}, url = {https://github.com/SupreethRao99/searchLM},}| 0.608 |
| 5–7 |
| 0% |
| SFT v2 | 0.466 | 0.358 | 109 | ~65% |
| GRPO v2 ✅ | 0.577 | 0.657 | 147 | ~35% |
| ~25% |
frac_reward_zero_std (step 1) | 90–96% | 0.0% |
frac_reward_zero_std (final) | 90–96% | ~61% |
| Reasoning block | empty | substantive |
| 2,879 (~3.3s/step) |
| Batch size | 2 (+ 8 grad accum = effective 16) |
| Learning rate | 1e-6 |
| vLLM GPU utilisation | 0.30 (24 GB KV cache) |
| Max new tokens | 1,024 |
| Gradient checkpointing | yes |
| Hardware | NVIDIA H100 80 GB |
| Training time | ~3h 3m |
| Final train loss | 0.0012 |
| Final mean reward | ~0.29 |
| W&B run | supreethrao/searchlm/runs/9x1tg52j |
A OR Bcancer OR tumor OR malignancy |
| NOT | NOT A | NOT review |
| Grouping | (A OR B) | (cat OR feline) AND behavior |
| Field scope | field:term | title:"machine learning" |
| Boost | term^N | cancer^2 OR tumor |