Instructions to use AdarshSingh7647/Naive-SFT-Table-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdarshSingh7647/Naive-SFT-Table-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AdarshSingh7647/Naive-SFT-Table-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdarshSingh7647/Naive-SFT-Table-8B")
model = AutoModelForCausalLM.from_pretrained("AdarshSingh7647/Naive-SFT-Table-8B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdarshSingh7647/Naive-SFT-Table-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdarshSingh7647/Naive-SFT-Table-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdarshSingh7647/Naive-SFT-Table-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdarshSingh7647/Naive-SFT-Table-8B

SGLang

How to use AdarshSingh7647/Naive-SFT-Table-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AdarshSingh7647/Naive-SFT-Table-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdarshSingh7647/Naive-SFT-Table-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AdarshSingh7647/Naive-SFT-Table-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdarshSingh7647/Naive-SFT-Table-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdarshSingh7647/Naive-SFT-Table-8B with Docker Model Runner:
```
docker model run hf.co/AdarshSingh7647/Naive-SFT-Table-8B
```

AdarshSingh7647 commited on Sep 4

Commit

3f7b2be

verified ·

1 Parent(s): df7596b

Rebuild card: fix cross-links to renamed repos, simplify

Browse files

Files changed (1) hide show

README.md +11 -24

README.md CHANGED Viewed

@@ -3,29 +3,19 @@ license: apache-2.0
 base_model: Qwen/Qwen3-8B
 library_name: transformers
 pipeline_tag: text-generation
-tags:
-- table-ranking
-- listwise-reranking
-- table-retrieval
-- table-question-answering
-- qwen3
 language:
 - en
 ---
-# TabRank — Naive (Answer-Only)
-Part of the [TabRank](https://huggingface.co/collections/AdarshSingh7647/tabrank-qwen3-8b-table-rerankers) family: Qwen3-8B checkpoints for **single-call generative listwise table reranking**. Given a question and a list of candidate tables, the model reads them all in one prompt and returns the full ranking in a single generation — no pairwise scoring, no cross-encoder passes.
 ![TabRank: question and candidate tables go into a single Qwen3-8B call, which reasons and emits a ranked list](tabrank_task.png)
-This checkpoint is the **Naive (Answer-Only)** variant: fine-tuned to output the ranking directly, with no reasoning trace, so it is the fastest of the three objectives at inference time. It is trained on **NQ Tables + MultiTabQA**.
-For the reasoning variants trained on the same data, see [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) (standard CoT SFT) and [TabRank](https://huggingface.co/AdarshSingh7647/TabRank) (our best method). Family: **TabRankNaive** (this model) · [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) · [TabRank](https://huggingface.co/AdarshSingh7647/TabRank).
-## How it works
-TabRank is trained on 6,728 chain-of-thought reasoning traces distilled from a teacher model reasoning about table relevance. This variant drops the reasoning trace and trains only on the final ranking, so at inference it goes straight from input to output. The training mix adds MultiTabQA questions that require reasoning over more than one table, which is where this data mix helps generalization the most (see the [paper](https://arxiv.org/abs/2607.25182)).
 ## Input / output format
@@ -61,9 +51,9 @@ Map the numbers back to your own table ids to get the reranked list — position
 ## Evaluation
-This card does not publish a verified in-distribution results table (SQA/TAT-QA/HybridQA/TabFact) for the Naive objective on this training mix — earlier published numbers for this specific checkpoint could not be confirmed against source eval logs, so rather than risk repeating an error we're leaving them out until they're re-run and verified.
-For a trustworthy, fully-verified comparison, see the results tables on [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) and [TabRank](https://huggingface.co/AdarshSingh7647/TabRank) (our best method), which include both in-distribution results and out-of-distribution results on 8 benchmarks from the [IBM table-text-ir-evaluation suite](https://huggingface.co/collections/ibm-research/table-text-ir-evaluation). Source eval code and logs are in the [GitHub repo](https://github.com/AdarshSingh7647/TabRanker).
 ## Usage with vLLM
@@ -108,20 +98,17 @@ out = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95,
 print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
 ```
-For full training and evaluation code, dataset builders, and the reasoning-trace dataset, see the [TabRanker GitHub repo](https://github.com/AdarshSingh7647/TabRanker).
 ## Model details
 * Base model: Qwen3-8B
-* Method: LoRA rank 16 fine-tuning, merged into the base weights so it loads directly
-* Precision: bfloat16, single-file safetensors, ~16 GB
-* Training data: NQ Tables + MultiTabQA (single- and multi-table retrieval)
-* Family: three TabRank checkpoints — **TabRankNaive** (this model — no reasoning, fastest), [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) (standard CoT SFT), and [TabRank](https://huggingface.co/AdarshSingh7647/TabRank) (reasoning-conditioned, best generalization)
 ## Citation
-If you use these models, please cite the TabRank paper:
 ```bibtex
 @misc{singh2026tabrank,
       title={TabRank: Chain-of-Thought Distillation for Table Re-Rankers},
@@ -134,7 +121,7 @@ If you use these models, please cite the TabRank paper:
 }
 ```
-The MultiTabQA data in this checkpoint's training mix comes from RAG over Tables. If your usage relies specifically on the multi-table data, please also cite:
 ```bibtex
 @misc{zou2025ragtableshierarchicalmemory,

 base_model: Qwen/Qwen3-8B
 library_name: transformers
 pipeline_tag: text-generation
 language:
 - en
 ---
+# TabRankNaive
+Qwen3-8B, fine-tuned for **single-call generative listwise table reranking**. Given a question and a list of candidate tables, it reads them all in one prompt and returns the full ranking in a single generation — no pairwise scoring, no cross-encoder passes.
 ![TabRank: question and candidate tables go into a single Qwen3-8B call, which reasons and emits a ranked list](tabrank_task.png)
+This checkpoint is the **Answer-Only** variant: fine-tuned to output the ranking directly with no reasoning trace, so it's the fastest of the three objectives at inference.
+Related: [TabRank](https://huggingface.co/AdarshSingh7647/TabRank) (same data, reasoning-conditioned, our best method) · [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) (same data, standard CoT SFT).
 ## Input / output format
 ## Evaluation
+This card does not publish a verified results table for the Answer-Only objective on this training mix — earlier published numbers for this checkpoint could not be confirmed against source eval logs, so they're left out rather than risk repeating an error.
+For a fully-verified comparison, see [TabRankStandardSFT](https://huggingface.co/AdarshSingh7647/TabRankStandardSFT) and [TabRank](https://huggingface.co/AdarshSingh7647/TabRank), which include in-distribution results (SQA, TAT-QA, HybridQA, TabFact, NQ-Tables) and out-of-distribution results on 7 benchmarks from the [IBM table-text-ir-evaluation suite](https://huggingface.co/collections/ibm-research/table-text-ir-evaluation). Source eval code and logs: [GitHub](https://github.com/AdarshSingh7647/TabRanker).
 ## Usage with vLLM
 print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
 ```
+Full training and eval code: [github.com/AdarshSingh7647/TabRanker](https://github.com/AdarshSingh7647/TabRanker).
 ## Model details
 * Base model: Qwen3-8B
+* Method: LoRA rank 16, merged into base weights
+* Precision: bfloat16, ~16 GB
+* Training data: NQ Tables + MultiTabQA
 ## Citation
 ```bibtex
 @misc{singh2026tabrank,
       title={TabRank: Chain-of-Thought Distillation for Table Re-Rankers},
 }
 ```
+The MultiTabQA data in this checkpoint's training mix comes from RAG over Tables:
 ```bibtex
 @misc{zou2025ragtableshierarchicalmemory,