From: blaze999 <huggingface.co/blaze999> Newsgroups: alt.freeweights.visionSubject: Medical-NER Date: 2026-11-15Commit: a9d5061Signed: 2DC28CC7B26A283B ✓ Token classification model with 184M parameters. Safetensors weights, 747 MB in all. Published by blaze999 under MIT.
184M params 747 MB Medical-NER safetensors permissive
Facts Params 184M Size 747 MB Formats safetensors Task token classification License MIT permissive
fw
$ fw get blaze999/Medical-NER
# manifest sha256 52b9159dba7b… · 747 MB · 10 files
$ fw verify ./Medical-NER blaze999/Medical-NERHosted (signed) blaze999/Medical-NER Last check: 2026-11-15 02:43 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Overview
Size 747 MB
Weights 736 MB (safetensors)
Parameters 184M
Formats safetensors
Task token classification
License MIT (permissive)
Files 10, each with a sha256
Publisher blaze999
Added 2026-11-15
Section alt.freeweights.vision Lineage
Original release from the publisher.
Base model: microsoft/deberta-v3-base
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 02:43 UTC passed
Model card From the publisher at commit
a9d5061 . Shown as plain text with links; images open at the publisher.
deberta-med-ner-2#
This model is a fine-tuned version of DeBERTa on the PubMED Dataset.
Model description#
Medical NER Model finetuned on BERT to recognize 41 Medical entities.
Training hyperparameters#
The following hyperparameters were used during training:
learning_rate: 2e-05 train_batch_size: 8 eval_batch_size: 16 seed: 42 gradient_accumulation_steps: 2 total_train_batch_size: 16 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: cosine lr_scheduler_warmup_ratio: 0.1 num_epochs: 30 mixed_precision_training: Native AMP Usage#
The easiest way is to load the inference api from huggingface and second method is through the pipeline object offered by transformers library.
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("token-classification", model="Clinical-AI-Apollo/Medical-NER", aggregation_strategy='simple')
result = pipe('45 year old woman diagnosed with CAD')
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("Clinical-AI-Apollo/Medical-NER")
model = AutoModelForTokenClassification.from_pretrained("Clinical-AI-Apollo/Medical-NER")Author#
Author: Saketh Mattupalli
Framework versions#
Transformers 4.37.0 Pytorch 2.1.2 Datasets 2.1.0 Tokenizers 0.15.1 Files 10 files · 747 MB Weights 736 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 2.49 KB 25fe879f6eebffe55e48a13622c613b4b67b327e6540b26552a048003880be29 added_tokens.json 23 B dc046d04c9b0ada7ae6f1dc89c465801799acdf0c9a6aab8c15a1b2d5ca4e91f config.json 5.14 KB 95ac7e777dd3d118d09dce4f66beffc1a17e428edcf3c359849a26ade02f3936 model.safetensors 736 MB 9fa0137fc2d0383aefa8cbb7dcce0e85ccc7f88290951419ac54a160343aaf7d special_tokens_map.json 286 B 9463f61e1b109a8eb4688b829260d7c6b1e6dff04c98ff7269bb89e2b92369b9 spm.model 2.46 MB c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd tokenizer.json 8.66 MB f0a66ad0d735d8dca9ecac4ff50fcdef4bb6adbadd2941a926844844d2c2059b tokenizer_config.json 1.28 KB 557b3d33d3f41b81ad769244e506549e98a1857d41dd58160aacd4d98d710b5a training_args.bin 4.66 KB d82257d8194d3d25a29011a6bfec613c3acf7495068de099fcd2d8f178a32419
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents a9d5061193 pinned now 2026-11-15 02:43 UTC 10 files · 747 MB
Use it fw
$ fw get blaze999/Medical-NER
# manifest sha256 52b9159dba7b… · 747 MB · 10 files
$ fw verify ./Medical-NER blaze999/Medical-NERfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/blaze999/Medical-NER.json --dir ./Medical-NER
$ python3 fw.py verify ./Medical-NER ./blaze999__Medical-NER.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download blaze999/Medical-NER --revision a9d5061193e969de80b24225f926cb224caac1ce --local-dir ./Medical-NERLicense Name MIT License Id MIT Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 25fe879f6eebffe55e48a13622c613b4b67b327e6540b26552a048003880be29 Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: blaze999 <huggingface.co/blaze999> Newsgroups: alt.freeweights.visionSubject: Medical-NER Date: 2026-11-15Commit: a9d5061Signed: 2DC28CC7B26A283B ✓
Upstream blaze999/Medical-NER Pinned commit a9d5061193e969de80b24225f926cb224caac1ce Manifest Medical-NER.json · .minisig Manifest sha256 52b9159dba7b7fd350507a3c810c3fbd26d688c2eb76fad07d0360596d95f9be Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 02:43 UTC Generator freeweights-manifest/0.1.0 Takedowns None. How to verify
$ curl -O https://freeweights.allternit.com/manifests/blaze999/Medical-NER.json
$ curl -O https://freeweights.allternit.com/manifests/blaze999/Medical-NER.json.minisig
$ minisign -Vm Medical-NER.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree 1 model in the catalog name this one as their parent.
Quantizations 1
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download blaze999/Medical-NEROpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
Variants
1 quantized or adapter build of Medical-NER. Each has its own license check and page.
86M params 4.81 GB ai_vs_real_image_detection safetensors permissive Facts Params 86M Size 4.81 GB Formats safetensors Task image classification License Apache-2.0 permissive flip From: dima806 <huggingface.co/dima806> Subject: ai_vs_real_image_detection 88M params 350 MB AI-Anime-Image-Detector-ViT safetensors permissive Facts Params 88M Size 350 MB Formats safetensors Task image classification License Apache-2.0 permissive flip From: legekka <huggingface.co/legekka> Subject: AI-Anime-Image-Detector-ViT vision 969 MB AI-Anime-Image-Detector-ViT-ONNX onnx permissive Facts Params not stated Size 969 MB Formats onnx Task image classification License Apache-2.0 permissive flip From: <huggingface.co/onnx-community> Subject: AI-Anime-Image-Detector-ViT-ONNX 150M params 602 MB answerdotai-ModernBERT-base-ai-detector safetensors permissive Facts Params 150M Size 602 MB Formats safetensors Task text classification License Apache-2.0 permissive flip From: AICodexLab <huggingface.co/AICodexLab> Subject: answerdotai-ModernBERT-base-ai-detector vision 1.94 GB answerdotai-ModernBERT-base-ai-detector-ONNX onnx permissive Facts Params not stated Size 1.94 GB Formats onnx Task text classification License Apache-2.0 permissive flip From: <huggingface.co/onnx-community> Subject: answerdotai-ModernBERT-base-ai-detector-ONNX vision 13.6 GB bart-large-cnn-ONNX onnx permissive Facts Params not stated Size 13.6 GB Formats onnx Task not tagged License MIT permissive flip From: <huggingface.co/onnx-community> Subject: bart-large-cnn-ONNX
