yasserrmd / gastroenterology-gemma-300m-emb

huggingface.co
Total runs: 88
24-hour runs: 0
7-day runs: 10
30-day runs: 20
Model's Last Updated: September 20 2025
sentence-similarity

Introduction of gastroenterology-gemma-300m-emb

Model Details of gastroenterology-gemma-300m-emb

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m . It maps sentences & paragraphs to a 768-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: google/embeddinggemma-300m
  • Maximum Sequence Length: 2048 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity
Model Sources
Full Model Architecture
SentenceTransformer(
  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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("yasserrmd/gastroenterology-gemma-300m-emb")
# Run inference
queries = [
    "What are the hepatic manifestations and treatment options for individuals with Alagille syndrome (ALGS)?",
]
documents = [
    'The hepatic manifestations of ALGS typically include severe pruritus and disfiguring xanthomas. Treatment options for ALGS-related liver disease primarily involve supportive measures, such as choleretic agents (e.g., ursodeoxycholic acid), medications for itch relief (e.g., cholestyramine, rifampin, naltrexone), and surgical biliary diversion procedures (e.g., partial internal biliary diversion, ileal exclusion). The Kasai procedure, commonly used for biliary atresia, is not recommended for ALGS individuals as it may worsen the outcome. Liver transplantation is also an option and has shown an 80% 5-year survival rate, with most affected individuals experiencing catch-up growth.',
    'The Kimura-Takemoto classification is a system used to assess gastric mucosal atrophy. It identifies different atrophic patterns based on characteristic features observed during endoscopy. These patterns include C1 (atrophic mucosa in the antrum only), C2 (atrophic mucosa at the gastric angle or in the lower corpus), C3 (atrophic mucosa also found in the upper corpus), O1 (atrophic mucosa surrounds the gastric cardia, but the folds of the great curvature are maintained), O3 (entire gastric mucosa is atrophic, and the folds of the greater curvature disappear), and O2 (an intermediate condition between O1 and O3).',
    'Probiotics are living microorganisms that can have beneficial effects on the body. Studies have shown that probiotics can effectively attenuate alcoholic liver disease and improve liver function. They achieve these effects by maintaining the balance of intestinal microbiota, activating the endogenous microbial community, and regulating the immune system. Probiotics have been used in the treatment of alcoholic liver disease, with some strains, such as Lactobacillus rhamnosus GG (LGG), showing effectiveness in increasing the number of beneficial bacteria in the gut and altering serum levels of certain liver enzymes and bilirubin.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.6757, 0.0341, 0.0612]])
Training Details
Training Dataset
Unnamed Dataset
  • Size: 20,000 training samples
  • Columns: sentence_0 and sentence_1
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1
    type string string
    details
    • min: 8 tokens
    • mean: 21.43 tokens
    • max: 49 tokens
    • min: 17 tokens
    • mean: 87.31 tokens
    • max: 241 tokens
  • Samples:
    sentence_0 sentence_1
    What are the benefits of combining high dose IV PPI with endoscopic treatment for peptic ulcer rebleeding management?
    Combining high dose IV PPI with endoscopic treatment for peptic ulcer rebleeding management has been shown to be significantly better than administering high dose IV PPI alone. It reduces the rebleeding rate, with a rebleeding rate of 0% compared to 9% when high dose IV PPI is administered alone. However, there is no significant difference in terms of mortality rate between the two approaches.
    How can non-invasive methods be used to diagnose and evaluate schistosome-induced liver fibrosis? Non-invasive methods, such as ultrasonography, CT, MRI, and serum markers, can be used to diagnose and evaluate schistosome-induced liver fibrosis. Liver biopsy, although considered the gold standard, is clinically impractical in the field. Ultrasonography is valuable in assessing pathology, but its availability is limited in many endemic communities. CT and MRI show distinct imaging features associated with hepatosplenic schistosomiasis and aid in diagnosis and clinical management. Serum markers, such as hyaluronic acid, collagen type III, YKL-40, and laminin, show promise in evaluating hepatic fibrosis. However, more studies are needed to evaluate the utility of other markers, such as matrix metalloproteinases, inhibitors, and cytokines.
    What are the typical symptoms and complications associated with Meckel's diverticulum? Meckel's diverticulum can present with symptoms such as hemorrhage, obstruction, perforation, and inflammation. The reported lifetime complication rate is 4%.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim",
        "gather_across_devices": false
    }
    
Training Hyperparameters
Non-Default Hyperparameters
  • per_device_train_batch_size : 6
  • per_device_eval_batch_size : 6
  • num_train_epochs : 1
  • multi_dataset_batch_sampler : round_robin
All Hyperparameters
Click to expand
  • overwrite_output_dir : False
  • do_predict : False
  • eval_strategy : no
  • prediction_loss_only : True
  • per_device_train_batch_size : 6
  • per_device_eval_batch_size : 6
  • per_gpu_train_batch_size : None
  • per_gpu_eval_batch_size : None
  • 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 : 1
  • max_steps : -1
  • lr_scheduler_type : linear
  • lr_scheduler_kwargs : {}
  • warmup_ratio : 0.0
  • warmup_steps : 0
  • log_level : passive
  • log_level_replica : warning
  • log_on_each_node : True
  • logging_nan_inf_filter : True
  • save_safetensors : True
  • save_on_each_node : False
  • save_only_model : False
  • restore_callback_states_from_checkpoint : False
  • no_cuda : False
  • use_cpu : False
  • use_mps_device : False
  • seed : 42
  • data_seed : None
  • jit_mode_eval : False
  • use_ipex : False
  • bf16 : False
  • fp16 : False
  • fp16_opt_level : O1
  • half_precision_backend : auto
  • bf16_full_eval : False
  • fp16_full_eval : False
  • tf32 : None
  • local_rank : 0
  • ddp_backend : None
  • tpu_num_cores : None
  • tpu_metrics_debug : False
  • debug : []
  • dataloader_drop_last : False
  • dataloader_num_workers : 0
  • dataloader_prefetch_factor : None
  • past_index : -1
  • disable_tqdm : False
  • remove_unused_columns : True
  • label_names : None
  • load_best_model_at_end : False
  • ignore_data_skip : False
  • fsdp : []
  • fsdp_min_num_params : 0
  • fsdp_config : {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap : None
  • 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_fused
  • optim_args : None
  • adafactor : False
  • group_by_length : False
  • length_column_name : length
  • 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
  • use_legacy_prediction_loop : False
  • 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_inputs_for_metrics : False
  • include_for_metrics : []
  • eval_do_concat_batches : True
  • fp16_backend : auto
  • push_to_hub_model_id : None
  • push_to_hub_organization : None
  • mp_parameters :
  • auto_find_batch_size : False
  • full_determinism : False
  • torchdynamo : None
  • ray_scope : last
  • ddp_timeout : 1800
  • torch_compile : False
  • torch_compile_backend : None
  • torch_compile_mode : None
  • include_tokens_per_second : False
  • include_num_input_tokens_seen : False
  • 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 : False
  • prompts : None
  • batch_sampler : batch_sampler
  • multi_dataset_batch_sampler : round_robin
  • router_mapping : {}
  • learning_rate_mapping : {}
Training Logs
Epoch Step Training Loss
0.1500 500 0.0194
0.2999 1000 0.0169
0.4499 1500 0.0132
0.5999 2000 0.0042
0.7499 2500 0.0048
0.8998 3000 0.0034
Framework Versions
  • Python: 3.12.11
  • Sentence Transformers: 5.1.0
  • Transformers: 4.56.2
  • PyTorch: 2.8.0+cu128
  • Accelerate: 1.10.1
  • Datasets: 4.0.0
  • Tokenizers: 0.22.1
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",
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Runs of yasserrmd gastroenterology-gemma-300m-emb on huggingface.co

88
Total runs
0
24-hour runs
0
3-day runs
10
7-day runs
20
30-day runs

More Information About gastroenterology-gemma-300m-emb huggingface.co Model

gastroenterology-gemma-300m-emb huggingface.co

gastroenterology-gemma-300m-emb huggingface.co is an AI model on huggingface.co that provides gastroenterology-gemma-300m-emb's model effect (), which can be used instantly with this yasserrmd gastroenterology-gemma-300m-emb model. huggingface.co supports a free trial of the gastroenterology-gemma-300m-emb model, and also provides paid use of the gastroenterology-gemma-300m-emb. Support call gastroenterology-gemma-300m-emb model through api, including Node.js, Python, http.

gastroenterology-gemma-300m-emb huggingface.co Url

https://huggingface.co/yasserrmd/gastroenterology-gemma-300m-emb

yasserrmd gastroenterology-gemma-300m-emb online free

gastroenterology-gemma-300m-emb huggingface.co is an online trial and call api platform, which integrates gastroenterology-gemma-300m-emb's modeling effects, including api services, and provides a free online trial of gastroenterology-gemma-300m-emb, you can try gastroenterology-gemma-300m-emb online for free by clicking the link below.

yasserrmd gastroenterology-gemma-300m-emb online free url in huggingface.co:

https://huggingface.co/yasserrmd/gastroenterology-gemma-300m-emb

gastroenterology-gemma-300m-emb install

gastroenterology-gemma-300m-emb is an open source model from GitHub that offers a free installation service, and any user can find gastroenterology-gemma-300m-emb on GitHub to install. At the same time, huggingface.co provides the effect of gastroenterology-gemma-300m-emb install, users can directly use gastroenterology-gemma-300m-emb installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

gastroenterology-gemma-300m-emb install url in huggingface.co:

https://huggingface.co/yasserrmd/gastroenterology-gemma-300m-emb

Url of gastroenterology-gemma-300m-emb

gastroenterology-gemma-300m-emb huggingface.co Url

Provider of gastroenterology-gemma-300m-emb huggingface.co

yasserrmd
ORGANIZATIONS

Other API from yasserrmd

huggingface.co

Total runs: 28
Run Growth: 3
Growth Rate: 10.71%
Updated:October 19 2025