GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Cyrax321
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Cyrax321
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-8B teaching the output
contract (SQL: / ANSWER: with [table:row_id] citations, or
REFUSAL:), schema terminology, and calibrated refusal.Qwen/Qwen3-8B + the same
retrieval achieves the fact-bearing part; per the v1.1 finding,
fine-tuning taught style, not facts - this release is built on that
constraint.| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen3-8B |
| Method | QLoRA, 4-bit NF4, double quantization |
| LoRA | r=16, alpha=32, dropout=0.05, targets=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'] |
| Optimizer | lr=0.0001, cosine schedule, warmup 0.03, 3 epochs |
| Batch | 1 per device x 16 grad accum, max_len 4096 |
| Decoding (pinned) | non-thinking mode, T=0.7, top_p=0.8, top_k=20 |
| Training data | RAFT-style triples from 30 questions (10 train_ok; held-out questions never trained) |
| Mix | ~70% grounded / ~15% refusal / ~15% schema-only, hard-negative distractors |
| Seed | 1 |
Training data construction, distractor sampling, and the refusal mix are
produced by the harness (triples stage) and are reproducible from the repo.
All numbers below come from captured run artifacts
(report.md, failures/), produced by the same harness on identical
questions with byte-identical frozen evidence packs for every system.
(Evaluation pending - this card is generated from the training run only. The results table lands here after the eval matrix runs.)
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", device_map="auto")model = PeftModel.from_pretrained(base, "QwerySmith-2.0-dev-seed1")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B") # The model expects the harness prompt contract:# SYSTEM contract + SCHEMA (CREATE TABLE text)# + QUESTION + RETRIEVED EVIDENCE rows as [table:row_id] lines# and emits either:# SQL: <one SELECT> / ANSWER: <text with [table:row_id] citations># or REFUSAL: <what is missing>Execute generated SQL read-only, with a statement timeout and an AST SELECT-only guard (the harness ships one).
figures/loss_curve_seed1.png | training loss + LR schedule |
figures/results_table.png | the evaluation table, as measured |
figures/ + card diagram | pipeline & inference contract (below) |
text
QWERYSMITH 2.0 - ARCHITECTURE & PIPELINE================================================================================ RAW CSVs PREPARE (CPU, local) TRAIN (T4, Colab)============ ========================= ================== 9 Olist tables -> ingest -> Postgres/SQLite RAFT triples jsonl -> QLoRA profile -> cutoff frozen TRIPLE | validate -> leak checks BUILDER v retrieve -> evidence packs ~70/15/15 Qwen3-8B 4-bit triples -> training data grounded/ + LoRA r16 a32 (train_ok only) refusal/ lr 1e-4 cosine schema 3 seeds================================================================================ EVAL MATRIX (L4, Colab) - identical questions + identical frozen packs=============================================================================== row 1 Qwen3-8B base + packs --> scorer --> EX / flip / refusal row 2 Qwen3-8B + adapter + packs --> scorer --> mean of 3 seeds row 3 Qwen3-30B-A3B AWQ + packs --> scorer --> on-prem alternative row 4 frontier (API) + packs --> scorer --> reference | McNemar + GATE (pre-registered) <- report.md + failures/ ================================================================================ INFERENCE CONTRACT (what the fine-tune teaches - behaviour only)=============================================================================== prompt = SYSTEM contract + SCHEMA (CREATE TABLE text) + QUESTION + RETRIEVED EVIDENCE [table:row_id] rows | v SQL: <one SELECT statement> ANSWER: <text with [table:row_id] citations> or REFUSAL: <why> | v sandboxed execution (read-only role, 30s timeout, sqlglot AST guard) facts ALWAYS come from retrieval - the adapter never stores dataTrained by the QwerySmith v3 harness (one-command reproducible): see repository
Hardware: Tesla T4, 14912 MB VRAM; packages: {"torch": "2.11.0+cu128", "transformers": "5.5.0", "trl": "0.24.0", "peft": "0.20.0", "unsloth": "2026.9.11", "datasets": "4.3.0", "bitsandbytes": "0.50.2"}
v1.x lineage (1.0/1.1 fine-tuning pipeline and its evaluation):
see the repository's legacy/ directory.
Apache-2.0 (base model license). Dataset retains CC BY 4.0 (UCI Machine Learning Repository).
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", device_map="auto")model = PeftModel.from_pretrained(base, "QwerySmith-2.0-dev-seed1")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B") # The model expects the harness prompt contract:# SYSTEM contract + SCHEMA (CREATE TABLE text)# + QUESTION + RETRIEVED EVIDENCE rows as [table:row_id] lines# and emits either:# SQL: <one SELECT> / ANSWER: <text with [table:row_id] citations># or REFUSAL: <what is missing> QWERYSMITH 2.0 - ARCHITECTURE & PIPELINE================================================================================ RAW CSVs PREPARE (CPU, local) TRAIN (T4, Colab)============ ========================= ================== 9 Olist tables -> ingest -> Postgres/SQLite RAFT triples jsonl -> QLoRA profile -> cutoff frozen TRIPLE | validate -> leak checks BUILDER v retrieve -> evidence packs ~70/15/15 Qwen3-8B 4-bit triples -> training data grounded/ + LoRA r16 a32 (train_ok only) refusal/ lr 1e-4 cosine schema 3 seeds================================================================================ EVAL MATRIX (L4, Colab) - identical questions + identical frozen packs=============================================================================== row 1 Qwen3-8B base + packs --> scorer --> EX / flip / refusal row 2 Qwen3-8B + adapter + packs --> scorer --> mean of 3 seeds row 3 Qwen3-30B-A3B AWQ + packs --> scorer --> on-prem alternative row 4 frontier (API) + packs --> scorer --> reference | McNemar + GATE (pre-registered) <- report.md + failures/================================================================================ INFERENCE CONTRACT (what the fine-tune teaches - behaviour only)=============================================================================== prompt = SYSTEM contract + SCHEMA (CREATE TABLE text) + QUESTION + RETRIEVED EVIDENCE [table:row_id] rows | v SQL: <one SELECT statement> ANSWER: <text with [table:row_id] citations> or REFUSAL: <why> | v sandboxed execution (read-only role, 30s timeout, sqlglot AST guard) facts ALWAYS come from retrieval - the adapter never stores data