GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AdarshSingh7647
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AdarshSingh7647
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
System prompt used at eval time:
You are a table relevance expert. Given a question and a set of candidate tables, rank them from most to least useful for answering the question. Reason in a
<think>...</think>block, then output exactly JSON with keyranked_tables.
The user message lists candidate tables as ### Table 1, ### Table 2, … The
model outputs (optionally after a <think> block) a JSON object:
json
{"ranked_tables": [3, 1, 5, 2, 4, ...]}where the integers are the 1-based candidate positions in the prompt, best first. Map them back to your table ids to obtain the reranked list.
Evaluated as a single-call listwise reranker (think mode) reordering the first-stage top-25 candidate list, on 4 out-of-domain table-QA datasets. SQA / TAT-QA use the full test set; HybridQA / TabFact use a fixed shared 500-query sample.
| Dataset | n | recall@10 | ndcg@10 | acc@10 | MRR |
|---|---|---|---|---|---|
| SQA | 148 | 0.918 | 0.741 | 0.865 | 0.687 |
| TAT-QA | 362 | 0.671 | 0.519 | 0.486 | 0.563 |
| HybridQA | 500 | 0.916 | 0.783 | 0.848 | 0.788 |
| TabFact | 500 | 0.776 | 0.688 | 0.628 | 0.765 |
| Mean | 0.820 | 0.683 | 0.707 | 0.701 |
acc@k = all gold tables within the top-k (strict). Metrics are identical in
definition to the TabRank evaluation harness.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "forge-CoTCond_merged" # or your uploaded repo idtok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") SYSTEM = ("You are a table relevance expert. Given a question and a set of candidate " "tables, rank them from most to least useful for answering the question. " "Reason in a <think>...</think> block, then output exactly JSON with key ranked_tables.")user = "Question: ...\n\n### Table 1\n...\n\n### Table 2\n...\n" # your listwise prompt msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)out = model.generate(**tok(text, return_tensors="pt").to(model.device), max_new_tokens=8192, temperature=0.6, top_p=0.95)print(tok.decode(out[0], skip_special_tokens=True))For high-throughput reranking use vLLM (loads directly, no LoRA flags).
model.safetensors (~16 GB).chat_template.jinja / tokenizer are the ones used at train time.This model is trained in part on the MultiTabQA data from RAG over Tables. Please cite:
bibtex
@misc{zou2025ragtableshierarchicalmemory, title={RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking}, author={Jiaru Zou and Dongqi Fu and Sirui Chen and Xinrui He and Zihao Li and Yada Zhu and Jiawei Han and Jingrui He}, year={2025}, eprint={2504.01346}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2504.01346},}The accompanying TabRank paper is currently under review; its citation will be added here once available on arXiv.
{"ranked_tables": [3, 1, 5, 2, 4, ...]}from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "forge-CoTCond_merged" # or your uploaded repo idtok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") SYSTEM = ("You are a table relevance expert. Given a question and a set of candidate " "tables, rank them from most to least useful for answering the question. " "Reason in a <think>...</think> block, then output exactly JSON with key ranked_tables.")user = "Question: ...\n\n### Table 1\n...\n\n### Table 2\n...\n" # your listwise prompt msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)out = model.generate(**tok(text, return_tensors="pt").to(model.device), max_new_tokens=8192, temperature=0.6, top_p=0.95)print(tok.decode(out[0], skip_special_tokens=True))@misc{zou2025ragtableshierarchicalmemory, title={RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking}, author={Jiaru Zou and Dongqi Fu and Sirui Chen and Xinrui He and Zihao Li and Yada Zhu and Jiawei Han and Jingrui He}, year={2025}, eprint={2504.01346}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2504.01346},}