Hugging Face's logo

DChak2000
/
qwen3-8B-trace-align2

Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
dense
Generated from Trainer
dataset_size:2979
loss:CosineSimilarityLoss
Model card Files
xet
 Community
qwen3-8B-trace-align2 / README.md
DChak2000's picture
DChak2000
LoRA fine-tuned for Prolog–NL trace alignment
aa938db verified
preview code
|
raw
history blame contribute delete
12 kB
metadata 
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:2979
  - loss:CosineSimilarityLoss
base_model: Qwen/Qwen3-Embedding-8B
widget:
  - source_sentence: >-
      The earliest predicate succeeded with the same date value in all three
      positions, yielding the resulting relationship.
    sentences:
      - 'Succeeded: patient_(alice_pays,bob)'
      - 'Succeeded: day_to_stamp("2004-01-01",1073001600.0)'
      - 'Succeeded: earliest([_20958,_20958,_20958],_20912)'
  - source_sentence: The date February 3, 2019 corresponds to the timestamp 1549238400.
    sentences:
      - 'Succeeded: day_to_stamp("2019-02-03",1549238400.0)'
      - 'Succeeded: s2_a_2_B(bob,_100,2014)'
      - 'Succeeded: var(_19068)'
  - source_sentence: >-
      Alice failed to meet the requirements of section 7703(b)(1) for the tax
      year 2017.
    sentences:
      - 'Failed: s7703_b_1(alice,_24064,_24076,2017)'
      - 'Succeeded: day_to_stamp("2017-12-31",1514764800.0)'
      - 'Succeeded: nonvar("2015-09-01")'
  - source_sentence: Alice does not satisfy section 2(b) for 2017.
    sentences:
      - 'Failed: "private home"=="usa"'
      - 'Succeeded: is_before("2017-02-03","2017-12-31")'
      - 'Failed: s2_b(alice,_19308,2017)'
  - source_sentence: Alice's wages for 2017 do not meet the requirements of section 3306(a)(1).
    sentences:
      - 'Failed: s7703_a(alice,_100,_20446,2017)'
      - 'Failed: s3306_a_1_is_wages(alice,2017,_19070,_19056)'
      - 'Failed: s7703(alice,_19652,_19664,2015)'
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on Qwen/Qwen3-Embedding-8B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-8B. It maps sentences & paragraphs to a 4096-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

  • Model Type: Sentence Transformer
  • Base model: Qwen/Qwen3-Embedding-8B
  • Maximum Sequence Length: 40960 tokens
  • Output Dimensionality: 4096 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 40960, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("DChak2000/qwen3-8B-trace-align2")
# Run inference
queries = [
    "Alice\u0027s wages for 2017 do not meet the requirements of section 3306(a)(1).",
]
documents = [
    'Failed: s3306_a_1_is_wages(alice,2017,_19070,_19056)',
    'Failed: s7703_a(alice,_100,_20446,2017)',
    'Failed: s7703(alice,_19652,_19664,2015)',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.8150, 0.5534, 0.3907]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 2,979 training samples
  • Columns: sentence_0, sentence_1, and label
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 label
    type string string float
    details
    • min: 5 tokens
    • mean: 22.83 tokens
    • max: 70 tokens
    • min: 6 tokens
    • mean: 23.49 tokens
    • max: 158 tokens
    • min: 0.0
    • mean: 0.85
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    The residence condition for the individual was not satisfied. Failed: residence_(_19762) 1.0
    Alice was not determined to be married as of the close of 2015 according to section 7703(a)(1). Failed: s7703_a_1(alice,_19640,_19652,_19906,2015) 1.0
    The application of section 1(c) failed because Alice, being married under section 7703, is not an unmarried individual subject to that tax. Failed: s1_c(alice,2017,_102,2600) 1.0
  • Loss: CosineSimilarityLoss with these parameters:
    {
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • torch_empty_cache_steps: None
  • learning_rate: 5e-05
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1
  • num_train_epochs: 3
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_ratio: None
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • enable_jit_checkpoint: False
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • use_cpu: False
  • seed: 42
  • data_seed: None
  • bf16: False
  • fp16: False
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: -1
  • ddp_backend: None
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • parallelism_config: None
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • group_by_length: False
  • length_column_name: length
  • project: huggingface
  • trackio_space_id: trackio
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • hub_revision: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • auto_find_batch_size: False
  • full_determinism: False
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • include_num_input_tokens_seen: no
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • liger_kernel_config: None
  • eval_use_gather_object: False
  • average_tokens_across_devices: True
  • use_cache: False
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss
1.3405 500 0.0676
2.6810 1000 0.0322

Framework Versions

  • Python: 3.10.19
  • Sentence Transformers: 5.2.2
  • Transformers: 5.0.0
  • PyTorch: 2.5.1+cu121
  • Accelerate: 1.12.0
  • Datasets: 4.5.0
  • Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers 

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}