-
unsloth/GLM-4.7-Flash-FP8-Dynamic
Text Generation • 30B • Updated • 92.7k • 28 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 13.4M • • 1.32k -
Qwen/Qwen3-30B-A3B-Instruct-2507-FP8
Text Generation • 31B • Updated • 604k • 130 -
cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit
Text Generation • 84B • Updated • 106k • 23
Dung Vo PRO
tuandunghcmut
AI & ML interests
None yet
Recent Activity
updated a dataset 12 days ago
tuandunghcmut/ternary-bonsai-memory-footprint-report published a dataset 12 days ago
tuandunghcmut/ternary-bonsai-memory-footprint-report updated a collection 15 days ago
Verified DatasetsOrganizations
Gemma 4 Text-Only
Vision+audio-stripped text-only checkpoints derived from the Gemma 4 any-to-any model family.
MT-LLM
Safety SFT
Document Layout Analysis Dataset
RL-Papers
LLM for Security Benchmarks/Datasets
Text Embedding Papers
Quantized versions of LLMs/MLLMs
-
tencent/Hunyuan-A13B-Instruct-GPTQ-Int4
Text Generation • 80B • Updated • 277 • 53 -
tencent/Hunyuan-A13B-Instruct-FP8
Text Generation • 80B • Updated • 192 • 33 -
unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF
Text Generation • 480B • Updated • 4.83k • 179 -
unsloth/Kimi-K2-Instruct-GGUF
Text Generation • 1T • Updated • 32.1k • 229
LLM Series
SLM
Benchmarks for evaluating LLMs/MLLMs
Multilingual Parallel Text Corpus
Verified Datasets
Qwen3.5 Text-Only
Vision-stripped text-only checkpoints derived from the Qwen3.5 multimodal model family.
Agentic Benchmarks
Tool Calling dataset for search domain
Post-training Dataset
Visual Chain-of-Thought Reasoning Benchmarks
Visual-CoT/GCoT related
EMPTY A
Multilingual Sentiment Analysis Dataset
LLM/MLLM (20B - 80B, fit on 1-2 A100/H100)
MLLM (100B - 300B)
Conversation Dataset
-
5CD-AI/Vietnamese-Multi-turn-Chat-Alpaca
Viewer • Updated • 12.7k • 98 • 28 -
5CD-AI/Vietnamese-Ecommerce-Multi-turn-Chat
Viewer • Updated • 1.48k • 21 • 8 -
5CD-AI/Vietnamese-Ecommerce-Alpaca
Viewer • Updated • 69.3k • 43 • 12 -
5CD-AI/Vietnamese-alpaca-gpt4-gg-translated
Viewer • Updated • 52k • 334 • 20
Multilingual Pretraining Corpus for Southeast Asian Language
A100/H100 80GB Serving
-
unsloth/GLM-4.7-Flash-FP8-Dynamic
Text Generation • 30B • Updated • 92.7k • 28 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 13.4M • • 1.32k -
Qwen/Qwen3-30B-A3B-Instruct-2507-FP8
Text Generation • 31B • Updated • 604k • 130 -
cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit
Text Generation • 84B • Updated • 106k • 23
Verified Datasets
Gemma 4 Text-Only
Vision+audio-stripped text-only checkpoints derived from the Gemma 4 any-to-any model family.
Qwen3.5 Text-Only
Vision-stripped text-only checkpoints derived from the Qwen3.5 multimodal model family.
MT-LLM
Agentic Benchmarks
Safety SFT
Tool Calling dataset for search domain
Document Layout Analysis Dataset
Post-training Dataset
RL-Papers
Visual Chain-of-Thought Reasoning Benchmarks
LLM for Security Benchmarks/Datasets
Visual-CoT/GCoT related
Text Embedding Papers
EMPTY A
Quantized versions of LLMs/MLLMs
-
tencent/Hunyuan-A13B-Instruct-GPTQ-Int4
Text Generation • 80B • Updated • 277 • 53 -
tencent/Hunyuan-A13B-Instruct-FP8
Text Generation • 80B • Updated • 192 • 33 -
unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF
Text Generation • 480B • Updated • 4.83k • 179 -
unsloth/Kimi-K2-Instruct-GGUF
Text Generation • 1T • Updated • 32.1k • 229
Multilingual Sentiment Analysis Dataset
LLM Series
LLM/MLLM (20B - 80B, fit on 1-2 A100/H100)
SLM
MLLM (100B - 300B)
Benchmarks for evaluating LLMs/MLLMs
Conversation Dataset
-
5CD-AI/Vietnamese-Multi-turn-Chat-Alpaca
Viewer • Updated • 12.7k • 98 • 28 -
5CD-AI/Vietnamese-Ecommerce-Multi-turn-Chat
Viewer • Updated • 1.48k • 21 • 8 -
5CD-AI/Vietnamese-Ecommerce-Alpaca
Viewer • Updated • 69.3k • 43 • 12 -
5CD-AI/Vietnamese-alpaca-gpt4-gg-translated
Viewer • Updated • 52k • 334 • 20
Multilingual Parallel Text Corpus
Multilingual Pretraining Corpus for Southeast Asian Language