# Multi-task Adaptation
Deepseek Ai DeepSeek R1 Distill Qwen 14B GGUF
DeepSeek-R1-Distill-Qwen-14B is an optimized large language model with a parameter scale of 14B, released by DeepSeek AI. It is distilled from the Qwen architecture and offers multiple GGUF quantization versions to improve performance.
Large Language Model
D
featherless-ai-quants
237
1
Fin Mpnet Base
This is a fine-tuned sentence-transformers model specifically optimized for financial document retrieval tasks while maintaining general performance.
Text Embedding Other
F
mukaj
131.16k
7
EXAONE 3.5 2.4B Fine Tuning
Hugging Face's Transformer model library supporting various natural language processing tasks
Large Language Model
Transformers

E
good593
65
2
Qwen2.5 14B YOYO V5
Apache-2.0
The fifth-generation Qwen2.5-YOYO model integrates features from multiple advanced models, optimizes the model merging formula, and supports a context length of 1 million tokens.
Large Language Model Supports Multiple Languages
Q
YOYO-AI
33
3
Cuckoo C4
MIT
Cuckoo is a small (300M parameters) information extraction model that efficiently extracts information by mimicking the next-word prediction paradigm of large language models
Large Language Model
Transformers

C
KomeijiForce
15
1
Qwq 32B Preview Pruned
No specific model information provided, likely a generic transformers library model
Large Language Model
Transformers

Q
LordNoah
110
2
Doge 20M Instruct
Apache-2.0
Doge 20M is a small language model based on dynamic masked attention mechanism, supporting instruction following and Q&A tasks.
Large Language Model
Transformers English

D
SmallDoge
5,010
4
Ruri Large V2
Apache-2.0
Ruri is a Japanese universal text embedding model, focusing on sentence similarity calculation and feature extraction, with support for long text processing.
Text Embedding Japanese
R
cl-nagoya
3,672
9
Conan Embedding V1 Q4 K M GGUF
Conan-embedding-v1 is a Chinese text embedding model developed by the Tencent BAC team, implemented based on the sentence-transformers library, suitable for various Chinese natural language processing tasks.
Text Embedding
C
lagoon999
30
7
Maux Gte Persian
This is a sentence-transformers model fine-tuned from Alibaba NLP/gte-multilingual-base, specifically designed for Persian semantic text tasks.
Text Embedding Other
M
xmanii
662
5
Tybert
Apache-2.0
A Turkish BERT model pre-trained by Trendyol, suitable for various natural language understanding tasks.
Large Language Model
Transformers Other

T
Trendyol
54
6
Xfinder Llama38it
xFinder-llama38it is a fine-tuned key answer extraction model based on Llama3-8B-Instruct, designed to improve the accuracy and robustness of key answer extraction from large language model outputs.
Large Language Model
Transformers English

X
IAAR-Shanghai
189
5
Llama 3 6B V0.1
The world's first 6-billion-parameter Llama-3 base model, created using the downgrade loop technique from Meta-Llama-3-8B and continuously pretrained on 1 billion English text tokens
Large Language Model
Transformers English

L
prince-canuma
14
14
Roberta Large InBedder
MIT
InBedder is a text embedder specifically designed to follow instructions, capable of capturing text features specified by user instructions through question-answering.
Text Embedding
Transformers English

R
BrandonZYW
17
2
Discogs Maest 30s Pw 129e
MAEST is a series of Transformer models based on PASST, focusing on music analysis applications, capable of classifying 400 music genres
Audio Classification
Transformers

D
mtg-upf
1,002
1
Instructor Xl
Apache-2.0
Instructor is an instruction-tuned text embedding model capable of generating customized text embedding vectors for any task and domain without additional fine-tuning.
Text Embedding
Transformers English

I
hkunlp
149.36k
566
Totally Harmless Model
This is a plain old model with unspecified specific functions and purposes.
Large Language Model
Transformers English

T
ykilcher
110
15
Opt 350m
Other
OPT is an open-source pre-trained Transformer language model developed by Meta AI, with parameter scales ranging from 125 million to 175 billion, designed to advance research in large-scale language models.
Large Language Model English
O
facebook
314.14k
141
Soongsilbert Base Beep
KoELECTRA is a Korean pre-trained language model based on the ELECTRA architecture, optimized for Korean natural language processing tasks.
Large Language Model Korean
S
jason9693
23
1
Rbt4
Apache-2.0
This is a Chinese pretrained BERT model using whole word masking strategy, released by the Harbin Institute of Technology-iFLYTEK Joint Laboratory to accelerate Chinese natural language processing research.
Large Language Model Chinese
R
hfl
22
6
Gpt Fr Cased Base
Apache-2.0
GPT-fr is a French GPT model developed by Quantmetry and the Laboratoire de Linguistique Formelle (LLF), trained on a large and diverse French corpus.
Large Language Model French
G
asi
755
28
Biom ALBERT Xxlarge
Large-scale biomedical language model based on BERT, ALBERT, and ELECTRA, specialized for biomedical domain tasks
Large Language Model
Transformers

B
sultan
77
2
Cpt Large
A pre-trained unbalanced Transformer model for Chinese understanding and generation, supporting various natural language processing tasks
Large Language Model
Transformers Chinese

C
fnlp
122
16
Deberta V2 Xlarge
MIT
DeBERTa V2 XXLarge is an enhanced natural language understanding model developed by Microsoft, which improves the BERT architecture through a disentangled attention mechanism and enhanced masked decoder, achieving SOTA performance on multiple NLP tasks.
Large Language Model
Transformers English

D
microsoft
116.71k
22
Biom ALBERT Xxlarge PMC
Large-scale biomedical language models based on BERT, ALBERT, and ELECTRA, achieving state-of-the-art results in multiple biomedical tasks
Large Language Model
Transformers

B
sultan
189
4
Chinese Legal Electra Base Generator
Apache-2.0
Chinese ELECTRA is a Chinese pre-trained model based on Google's ELECTRA, released by the HIT & iFLYTEK Joint Lab (HFL), featuring a compact structure and superior performance.
Large Language Model
Transformers Chinese

C
hfl
18
6
Hindi Bert
This is the first Hindi language model trained based on Google's ELECTRA framework, suitable for various Hindi NLP tasks.
Large Language Model
Transformers Other

H
monsoon-nlp
1,681
18
Bert Base Uncased Sparse 90 Unstructured Pruneofa
Apache-2.0
This is a sparsely pretrained BERT-Base model achieving 90% weight sparsity through one-shot pruning, suitable for fine-tuning on various language tasks.
Large Language Model
Transformers English

B
Intel
178
0
Bert Base Uncased Mnli Sparse 70 Unstructured No Classifier
This model is fine-tuned from bert-base-uncased-sparse-70-unstructured on the MNLI task (GLUE benchmark), with the classifier layer removed for easier loading into other downstream tasks for training.
Large Language Model
Transformers English

B
Intel
17
0
Featured Recommended AI Models