# Multi-task instruction fine-tuning
Velvet 2B
Apache-2.0
Velvet-2B is a 2-billion-parameter Italian-English bilingual large language model, trained from scratch based on the Transformer architecture, focusing on text generation and comprehension tasks.
Large Language Model
Transformers Supports Multiple Languages

V
Almawave
3,784
37
Hunyuan 7B Instruct 0124
Other
Hunyuan-7B is an open-source large language model released by Tencent. It has the ability to process 256K long texts and uses the Grouped Query Attention (GQA) mechanism, performing excellently among Chinese 7B dense models.
Large Language Model
Transformers English

H
tencent
590
50
Aceinstruct 72B
AceInstruct is a series of advanced SFT models, improved based on Qwen, suitable for coding, mathematics, and general tasks.
Large Language Model
Safetensors Supports Multiple Languages
A
nvidia
1,584
18
Dolphin3.0 Llama3.2 3B GGUF
A 3B-parameter large language model based on the Llama3.2 architecture, supporting English text generation tasks, quantized using llama.cpp with imatrix
Large Language Model English
D
bartowski
5,665
15
EVA Qwen2.5 72B V0.2
Other
A large language model fine-tuned based on Qwen2.5-72B, specializing in text generation and instruction-following tasks
Large Language Model
Transformers

E
EVA-UNIT-01
392
19
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
Mistral 7B Instruct Uz
Apache-2.0
Mistral-7B instruction fine-tuned model optimized for Uzbek, supporting various NLP tasks in Uzbek and English
Large Language Model
Transformers Supports Multiple Languages

M
behbudiy
49
13
Phi 3 Small 8k Instruct Onnx Cuda
MIT
Phi-3 Small is a 7B-parameter lightweight cutting-edge open-source model, optimized for NVIDIA GPUs in ONNX format, supporting 8K context length with strong inference capabilities.
Large Language Model
Transformers

P
microsoft
115
12
Bagel 8b V1.0
Other
An 8B parameter model built on Meta's Llama-3, fine-tuned using the Bagel dataset, and adopting a single llama-3 instruction format.
Large Language Model
Transformers

B
jondurbin
14.11k
53
Bagel 34b V0.2
Apache-2.0
An experimental fine-tuned model based on yi-34b-200k, suitable for creative writing, role-playing, and other tasks, without DPO stage applied.
Large Language Model
Transformers

B
jondurbin
265
41
Mistral 7b Yo Instruct
A model focused on Yoruba text generation, fine-tuned based on multiple datasets.
Large Language Model
Transformers Other

M
seyabde
18
2
Flan T5 Xl Gguf
Apache-2.0
FLAN-T5 is the instruction-fine-tuned version of the T5 model, optimized through fine-tuning on over 1,000 multilingual tasks, delivering superior performance at the same parameter count.
Large Language Model Supports Multiple Languages
F
deepfile
61
8
Platypus2 70B Instruct
Platypus2-70B-instruct is a large language model based on the LLaMA 2 architecture, created by merging models from garage-bAInd and upstageAI, focusing on instruction following and logical reasoning tasks.
Large Language Model
Transformers English

P
garage-bAInd
1,332
175
Manticore 13b
Manticore 13B is a large language model fine-tuned on multiple high-quality datasets based on the Llama 13B model, excelling in text generation tasks.
Large Language Model
Transformers English

M
openaccess-ai-collective
201
116
GPT JT 6B V1
Apache-2.0
GPT-JT is a large language model fine-tuned based on GPT-J (6B), utilizing UL2 training objectives, excelling in classification tasks
Large Language Model
Transformers English

G
togethercomputer
4,299
302
Featured Recommended AI Models