cometadata

funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

Training Pipeline

Trained on the cometadata/funding-extraction-artifact-data-mix-grpo-mixed-reward dataset using its pre-split sft / rl / test separations on the Tinker training service.

Stage 1: Supervised Fine-Tuning (SFT)

Base model: Qwen/Qwen3.5-9B
Data (data/sft/): 3,528 real + 7,240 synthetic funding statements with gold-standard funder/award labels (synthetic upsampled 2×)
Data augmentation: 50% of training examples augmented with synthetic noise (OCR-like case errors, digit/letter swaps, Unicode artifacts, XML/HTML tags, LaTeX markup)
Renderer: qwen3_5_disable_thinking (no chain-of-thought; keep thinking disabled at inference, see Usage)
LoRA rank: 128
Epochs: 2
Result: eval NLL 0.116 → 0.0035 over 252 steps

Stage 2: Reinforcement Learning (GRPO)

Algorithm: Group Relative Policy Optimization (GRPO) with importance sampling loss
Data (data/rl/): 1,160 real + 1,916 synthetic (train); 576 real + 968 synthetic (eval)
Reward: Hierarchical F0.5 scoring with binary funder/award-ID matching + flat award-ID association bonus
- reward = 0.50 * funder_F0.5 + 0.40 * hierarchical_award_id_F0.5 + 0.10 * flat_award_id_F0.5
- Funder matching — fuzzy (token_sort_ratio ≥ 0.80 threshold, Hungarian optimal assignment)
- Award ID matching — binary exact after normalization (strip whitespace/hyphens/slashes, uppercase), with soft (edit-distance-1) partial credit during training
- Flat award-ID term — awards partial credit when the correct award ID is extracted under the wrong funder, providing gradient on funder-award association errors
KL penalty: 0.03 (anchored to SFT checkpoint)
Group size: 8 rollouts per prompt
Temperature: 0.8
3e-5

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9384	0.9362	0.9373	0.9379	0.9369
Award ID	0.9069	0.8909	0.8988	0.9037	0.8957
Scheme	0.7407	0.8264

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8882	0.8960	0.8921	0.8897	0.8936
Award ID	0.8889	0.8732	0.8810	0.8857	0.8779
Scheme	0.6889	0.7686

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8796	0.8874	0.8835	0.8812	0.8850
Award ID	0.8859	0.8702	0.8780	0.8827	0.8750
Scheme	0.6667	0.7438

All 300 outputs were valid JSON.

funding-entity-extraction-dataset-mix test sets

Evaluated on the held-out test sets from cometadata/funding-entity-extraction-dataset-mix with the same evaluation harness. test_with_context uses the full_text field (the funding statement with its surrounding document text) as the model input.

`test.jsonl` (347 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9376	0.8923	0.9144	0.9282	0.9058
Award ID	0.8407	0.8339	0.8373	0.8394	0.8360
Scheme	0.4118	0.5927

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9008	0.8555	0.8776	0.8913	0.8689
Award ID	0.8138	0.8072	0.8105	0.8125	0.8092
Scheme	0.3725	0.5363

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8722	0.8276	0.8493	0.8629	0.8408
Award ID	0.7963	0.7898	0.7930	0.7949	0.7918
Scheme	0.3333	0.4798

`test_degraded.jsonl` (1,288 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9285	0.9216	0.9250	0.9271	0.9237
Award ID	0.8586	0.8560	0.8573	0.8581	0.8568
Scheme	0.7413	0.6704

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9001	0.8906	0.8953	0.8981	0.8935
Award ID	0.8416	0.8390	0.8403	0.8411	0.8398
Scheme	0.6757	0.6110

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8801	0.8690	0.8745	0.8778	0.8724
Award ID	0.8317	0.8291	0.8304	0.8312	0.8299
Scheme	0.6039	0.5461

`test_with_context.jsonl` (322 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9348	0.9383	0.9365	0.9355	0.9372
Award ID	0.8711	0.8690	0.8700	0.8707	0.8696
Scheme	0.7515	0.6844

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9072	0.9061	0.9066	0.9070	0.9064
Award ID	0.8538	0.8517	0.8527	0.8534	0.8523
Scheme	0.6871	0.6257

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8863	0.8842	0.8852	0.8859	0.8848
Award ID	0.8439	0.8418	0.8428	0.8434	0.8424
Scheme	0.6074	0.5531

Comparison to the Llama 3.1 8B baseline

Balanced-mode F1 on the two test sets reported by the Llama baseline card:

arxiv_test (300 examples)

Table with columns: Field, Llama 3.1 8B, Qwen3.5-9B, Δ
Field	Llama 3.1 8B	Qwen3.5-9B	Δ
Funder	0.9001	0.8921	−0.008
Award ID	0.8780	0.8810	+0.003
Scheme	0.6466	0.7266	+0.080
Title	0.5316	0.5507	+0.019

test_degraded (1,288 examples)

Table with columns: Field, Llama 3.1 8B, Qwen3.5-9B, Δ
Field	Llama 3.1 8B	Qwen3.5-9B	Δ
Funder	0.8999	0.8953	−0.005
Award ID	0.8477	0.8403	−0.007
Scheme	0.6370	0.6417	+0.005
Title	0.4110	0.3011	−0.110

Funder and award ID (the reward-weighted fields) are within 0.008 F1 of the Llama baseline on both sets. Scheme and title carry zero reward weight.

Usage

python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "cometadata/funding-extraction-qwen3.5-9B-artifact-data-mix-grpo-mixed-reward")
tokenizer = AutoTokenizer.from_pretrained("cometadata/funding-extraction-qwen3.5-9B-artifact-data-mix-grpo-mixed-reward")

prompt = """Extract funding information from the following statement:

This work was supported by the National Science Foundation under grant DMS-1613002 and by the NIH (R01-AI123456)."""

messages = [
    {"role": "system", "content": "You are an expert at extracting structured funding metadata from academic papers. Given a funding statement, extract all funders and their associated awards. Return a JSON array of funder objects. Each funder has:\n- \"funder_name\": string or null\n- \"awards\": array of objects with \"award_ids\" (array of strings), \"funding_scheme\" (array of strings), and \"award_title\" (array of strings)\nReturn ONLY the JSON array, no other text."},
    {"role": "user", "content": prompt},
]

# Model trained with thinking disabled; keep enable_thinking=False.
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True, enable_thinking=False
)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

Output Format

json
[
  {
    "funder_name": "National Science Foundation",
    "awards": [
      {
        "award_ids": ["DMS-1613002"],
        "funding_scheme": [],
        "award_title": []
      }
    ]
  },
  {
    "funder_name": "NIH",
    "awards": [
      {
        "award_ids": ["R01-AI123456"],
        "funding_scheme": [],
        "award_title": []
      }
    ]
  }
]

Model provider

cometadata

Model tree

Base

Qwen/Qwen3.5-9B

Adapter

this model

Modalities

Input

Video, Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

Explore FriendliAI today

Get started Talk to an engineer

Training Pipeline

Trained on the cometadata/funding-extraction-artifact-data-mix-grpo-mixed-reward dataset using its pre-split sft / rl / test separations on the Tinker training service.

Stage 1: Supervised Fine-Tuning (SFT)

Base model: Qwen/Qwen3.5-9B
Data (data/sft/): 3,528 real + 7,240 synthetic funding statements with gold-standard funder/award labels (synthetic upsampled 2×)
Data augmentation: 50% of training examples augmented with synthetic noise (OCR-like case errors, digit/letter swaps, Unicode artifacts, XML/HTML tags, LaTeX markup)
Renderer: qwen3_5_disable_thinking (no chain-of-thought; keep thinking disabled at inference, see Usage)
LoRA rank: 128
Epochs: 2
Result: eval NLL 0.116 → 0.0035 over 252 steps

Stage 2: Reinforcement Learning (GRPO)

Algorithm: Group Relative Policy Optimization (GRPO) with importance sampling loss
Data (data/rl/): 1,160 real + 1,916 synthetic (train); 576 real + 968 synthetic (eval)
Reward: Hierarchical F0.5 scoring with binary funder/award-ID matching + flat award-ID association bonus
- reward = 0.50 * funder_F0.5 + 0.40 * hierarchical_award_id_F0.5 + 0.10 * flat_award_id_F0.5
- Funder matching — fuzzy (token_sort_ratio ≥ 0.80 threshold, Hungarian optimal assignment)
- Award ID matching — binary exact after normalization (strip whitespace/hyphens/slashes, uppercase), with soft (edit-distance-1) partial credit during training
- Flat award-ID term — awards partial credit when the correct award ID is extracted under the wrong funder, providing gradient on funder-award association errors
KL penalty: 0.03 (anchored to SFT checkpoint)
Group size: 8 rollouts per prompt
Temperature: 0.8
3e-5

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9384	0.9362	0.9373	0.9379	0.9369
Award ID	0.9069	0.8909	0.8988	0.9037	0.8957
Scheme	0.7407	0.8264

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8882	0.8960	0.8921	0.8897	0.8936
Award ID	0.8889	0.8732	0.8810	0.8857	0.8779
Scheme	0.6889	0.7686

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8796	0.8874	0.8835	0.8812	0.8850
Award ID	0.8859	0.8702	0.8780	0.8827	0.8750
Scheme	0.6667	0.7438

All 300 outputs were valid JSON.

funding-entity-extraction-dataset-mix test sets

`test.jsonl` (347 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9376	0.8923	0.9144	0.9282	0.9058
Award ID	0.8407	0.8339	0.8373	0.8394	0.8360
Scheme	0.4118	0.5927

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9008	0.8555	0.8776	0.8913	0.8689
Award ID	0.8138	0.8072	0.8105	0.8125	0.8092
Scheme	0.3725	0.5363

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8722	0.8276	0.8493	0.8629	0.8408
Award ID	0.7963	0.7898	0.7930	0.7949	0.7918
Scheme	0.3333	0.4798

`test_degraded.jsonl` (1,288 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9285	0.9216	0.9250	0.9271	0.9237
Award ID	0.8586	0.8560	0.8573	0.8581	0.8568
Scheme	0.7413	0.6704

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9001	0.8906	0.8953	0.8981	0.8935
Award ID	0.8416	0.8390	0.8403	0.8411	0.8398
Scheme	0.6757	0.6110

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8801	0.8690	0.8745	0.8778	0.8724
Award ID	0.8317	0.8291	0.8304	0.8312	0.8299
Scheme	0.6039	0.5461

`test_with_context.jsonl` (322 examples)

Permissive (partial_ratio + token_set, no damping)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9348	0.9383	0.9365	0.9355	0.9372
Award ID	0.8711	0.8690	0.8700	0.8707	0.8696
Scheme	0.7515	0.6844

Balanced (length-damped + acronym detection)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.9072	0.9061	0.9066	0.9070	0.9064
Award ID	0.8538	0.8517	0.8527	0.8534	0.8523
Scheme	0.6871	0.6257

Strict (token_sort_ratio only)

Table with columns: Field, P, R, F1, F0.5, F1.5
Field	P	R	F1	F0.5	F1.5
Funder	0.8863	0.8842	0.8852	0.8859	0.8848
Award ID	0.8439	0.8418	0.8428	0.8434	0.8424
Scheme	0.6074	0.5531

Comparison to the Llama 3.1 8B baseline

Balanced-mode F1 on the two test sets reported by the Llama baseline card:

arxiv_test (300 examples)

Table with columns: Field, Llama 3.1 8B, Qwen3.5-9B, Δ
Field	Llama 3.1 8B	Qwen3.5-9B	Δ
Funder	0.9001	0.8921	−0.008
Award ID	0.8780	0.8810	+0.003
Scheme	0.6466	0.7266	+0.080
Title	0.5316	0.5507	+0.019

test_degraded (1,288 examples)

Table with columns: Field, Llama 3.1 8B, Qwen3.5-9B, Δ
Field	Llama 3.1 8B	Qwen3.5-9B	Δ
Funder	0.8999	0.8953	−0.005
Award ID	0.8477	0.8403	−0.007
Scheme	0.6370	0.6417	+0.005
Title	0.4110	0.3011	−0.110

Funder and award ID (the reward-weighted fields) are within 0.008 F1 of the Llama baseline on both sets. Scheme and title carry zero reward weight.

Usage

python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "cometadata/funding-extraction-qwen3.5-9B-artifact-data-mix-grpo-mixed-reward")
tokenizer = AutoTokenizer.from_pretrained("cometadata/funding-extraction-qwen3.5-9B-artifact-data-mix-grpo-mixed-reward")

prompt = """Extract funding information from the following statement:

This work was supported by the National Science Foundation under grant DMS-1613002 and by the NIH (R01-AI123456)."""

messages = [
    {"role": "system", "content": "You are an expert at extracting structured funding metadata from academic papers. Given a funding statement, extract all funders and their associated awards. Return a JSON array of funder objects. Each funder has:\n- \"funder_name\": string or null\n- \"awards\": array of objects with \"award_ids\" (array of strings), \"funding_scheme\" (array of strings), and \"award_title\" (array of strings)\nReturn ONLY the JSON array, no other text."},
    {"role": "user", "content": prompt},
]

# Model trained with thinking disabled; keep enable_thinking=False.
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True, enable_thinking=False
)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

Output Format

json
[
  {
    "funder_name": "National Science Foundation",
    "awards": [
      {
        "award_ids": ["DMS-1613002"],
        "funding_scheme": [],
        "award_title": []
      }
    ]
  },
  {
    "funder_name": "NIH",
    "awards": [
      {
        "award_ids": ["R01-AI123456"],
        "funding_scheme": [],
        "award_title": []
      }
    ]
  }
]

funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward

Get help setting up a custom Dedicated Endpoints.

README

Training Pipeline

Stage 1: Supervised Fine-Tuning (SFT)

Stage 2: Reinforcement Learning (GRPO)

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Balanced (length-damped + acronym detection)

Strict (token_sort_ratio only)

funding-entity-extraction-dataset-mix test sets

`test.jsonl` (347 examples)

`test_degraded.jsonl` (1,288 examples)

`test_with_context.jsonl` (322 examples)

Comparison to the Llama 3.1 8B baseline

Usage

Output Format

Explore FriendliAI today

README

Training Pipeline

Stage 1: Supervised Fine-Tuning (SFT)

Stage 2: Reinforcement Learning (GRPO)

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Balanced (length-damped + acronym detection)

Strict (token_sort_ratio only)

funding-entity-extraction-dataset-mix test sets

`test.jsonl` (347 examples)

`test_degraded.jsonl` (1,288 examples)

`test_with_context.jsonl` (322 examples)

Comparison to the Llama 3.1 8B baseline

Usage

Output Format

funding-extraction-qwen3.5-9B-non-thinking-artifact-data-mix-grpo-mixed-reward

Get help setting up a custom Dedicated Endpoints.

Training Pipeline

Stage 1: Supervised Fine-Tuning (SFT)

Stage 2: Reinforcement Learning (GRPO)

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Balanced (length-damped + acronym detection)

Strict (token_sort_ratio only)

funding-entity-extraction-dataset-mix test sets

test.jsonl (347 examples)

test_degraded.jsonl (1,288 examples)

test_with_context.jsonl (322 examples)

Comparison to the Llama 3.1 8B baseline

Usage

Output Format

Explore FriendliAI today

Training Pipeline

Stage 1: Supervised Fine-Tuning (SFT)

Stage 2: Reinforcement Learning (GRPO)

Evaluation Results

arxiv_test.jsonl (300 held-out examples)

Permissive (partial_ratio + token_set, no damping)

Balanced (length-damped + acronym detection)

Strict (token_sort_ratio only)

funding-entity-extraction-dataset-mix test sets

test.jsonl (347 examples)

test_degraded.jsonl (1,288 examples)

test_with_context.jsonl (322 examples)

Comparison to the Llama 3.1 8B baseline

Usage

Output Format

`test.jsonl` (347 examples)

`test_degraded.jsonl` (1,288 examples)

`test_with_context.jsonl` (322 examples)

`test.jsonl` (347 examples)

`test_degraded.jsonl` (1,288 examples)

`test_with_context.jsonl` (322 examples)