Ji-Xiang
Ji-Xiang
AI & ML interests
None yet
Recent Activity
updated
a collection
8 days ago
Vision liked
a model 8 days ago
microsoft/Phi-4-reasoning-vision-15B liked
a model 9 days ago
Qwen/Qwen3.5-35B-A3B Organizations
-
Qwen/QwQ-32B
Text Generation • Updated • 55.7k • • 2.89k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94.2k • • 752 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 959k • • 1.53k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • Updated • 1.71k • 270
Reinforcement Learning from Verifiable Rewards (RLVR) Datasets
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.25M • • 13.1k -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 959k • • 1.53k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94.2k • • 752 -
allenai/Llama-3.1-Tulu-3-70B
Text Generation • Updated • 917 • • 61
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 59.2k • 184 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 4.14k • 15 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 61.7k • 27 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 15.4k • 38
Critique Fine-Tuning (CFT) Datasets
Please see below：
https://medium.com/@techsachin/s1-simple-test-time-scaling-approach-to-exceed-openais-o1-preview-performance-ec5a624c5d2f
-
MediaTek-Research/Breeze-7B-Instruct-v0_1
Text Generation • 7B • Updated • 347 • 90 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 11 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 1.19k • 65 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 70 • 21
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 20.8k • 461 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 10.1k • 333 -
zai-org/cogvlm2-llama3-chat-19B
Text Generation • 20B • Updated • 2.59k • 219 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 18 • 3
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 59.2k • 184 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 4.14k • 15 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 61.7k • 27 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 15.4k • 38
-
Qwen/QwQ-32B
Text Generation • Updated • 55.7k • • 2.89k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94.2k • • 752 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 959k • • 1.53k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • Updated • 1.71k • 270
Critique Fine-Tuning (CFT) Datasets
Please see below：
https://medium.com/@techsachin/s1-simple-test-time-scaling-approach-to-exceed-openais-o1-preview-performance-ec5a624c5d2f
Reinforcement Learning from Verifiable Rewards (RLVR) Datasets
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.25M • • 13.1k -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 959k • • 1.53k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • Updated • 94.2k • • 752 -
allenai/Llama-3.1-Tulu-3-70B
Text Generation • Updated • 917 • • 61
-
MediaTek-Research/Breeze-7B-Instruct-v0_1
Text Generation • 7B • Updated • 347 • 90 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 11 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 1.19k • 65 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 70 • 21
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 20.8k • 461 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 10.1k • 333 -
zai-org/cogvlm2-llama3-chat-19B
Text Generation • 20B • Updated • 2.59k • 219 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 18 • 3