# 7B parameter scale
Deepseek Prover V2 7B Bf16
An MLX format model converted from DeepSeek-Prover-V2-7B, suitable for text generation tasks
Large Language Model
D
mlx-community
195
1
Qwen2.5 7B N8n
MIT
Qwen2.5-7B is a large language model with a 7B parameter scale based on the Qwen2 architecture, focusing on high-quality text generation tasks.
Large Language Model English
Q
npv2k1
249
3
Videochat R1 7B
Apache-2.0
VideoChat-R1_7B is a multimodal video understanding model based on Qwen2.5-VL-7B-Instruct, capable of processing video and text inputs and generating text outputs.
Video-to-Text
Transformers English

V
OpenGVLab
1,686
7
Mwm 7B CoT Merge1
This is a 7B-parameter language model merged using the mergekit tool, combining features from multiple instruction fine-tuned models
Large Language Model
Transformers

M
DataSoul
86
2
Stockqwen 2.5 7B
A multilingual large language model based on Qwen2.5-7B, integrating code, math, and general instruction-following capabilities
Large Language Model
Transformers Supports Multiple Languages

S
Locutusque
24
5
Japanese Starling ChatV 7B
Apache-2.0
A 7-billion-parameter Japanese dialogue model developed based on chatntq-ja-7b-v1.0, with original architecture derived from Mistral-7B-v0.1
Large Language Model
Transformers Japanese

J
TFMC
88
7
Flashbackmist Dare
Apache-2.0
test-dare is a merged model based on Mistral-7B, combining multiple Mistral-7B variants through the DARE method to integrate the strengths of each model.
Large Language Model
Transformers

F
FredrikBL
71
1
Eris Lelantacles 7b
Other
Eris-Lelanacles-7b is a large language model obtained by merging two 7B parameter models, Eris-Beach_Day-7b and Lelanta-lake-7b, using the SLERP method
Large Language Model
Transformers

E
ChaoticNeutrals
22
3
M7 7b
Apache-2.0
M7-7b is an experimental project that uses the mergekit tool to fuse multiple models with a 7B parameter scale, aiming to integrate the advantages of different models to improve performance.
Large Language Model
Transformers

M
liminerity
8,909
16
Saul 7B Instruct V1
MIT
A large instruction language model customized for the legal domain, obtained through continued pre-training based on Mistral-7B
Large Language Model
Transformers English

S
Equall
6,253
86
Mistral 7B Instruct V0.2 Turkish
Apache-2.0
Turkish instruction interaction model optimized through supervised fine-tuning based on Mistral-7B-Instruct-v0.2
Large Language Model
Transformers Supports Multiple Languages

M
malhajar
3,106
6
Geitje 7B Chat GPTQ
Apache-2.0
GEITje-7B-chat is a Dutch conversation model based on the Mistral architecture, specifically optimized for chat and dialogue tasks.
Large Language Model
Transformers Other

G
TheBloke
21
4
Mistral 7B V0.1 GGUF
Apache-2.0
Mistral 7B v0.1 is a 7-billion-parameter open-source large language model developed by Mistral AI, released under the Apache 2.0 license.
Large Language Model
M
TheBloke
17.17k
260
Xgen 7b 8k Base
Apache-2.0
A 7B-parameter large language model released by Salesforce AI Research, supporting 8K long sequence input, open-sourced under Apache-2.0 license
Large Language Model
Transformers

X
Salesforce
997
318
H2ogpt Gm Oasst1 En 2048 Open Llama 7b Preview 700bt
Apache-2.0
A large language model fine-tuned based on the OpenLlama 7B pre-trained model, trained with the OpenAssistant dataset, supporting English text generation tasks
Large Language Model
Transformers English

H
h2oai
58
4
Alpaca 7b Wdiff
Alpaca-7B is a large language model fine-tuned by Stanford University based on Meta's LLaMA-7B model, achieving better dialogue and task execution capabilities through instruction tuning.
Large Language Model
Transformers

A
tatsu-lab
106
57
Featured Recommended AI Models