Ji-Xiang
Ji-Xiang
AI & ML interests
None yet
Recent Activity
upvoted
an
article
4 days ago
We Got Claude to Fine-Tune an Open Source LLM
updated
a collection
15 days ago
text-to-speech (TTS)
liked
a model
15 days ago
Supertone/supertonic
Organizations
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 109k • 163 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 4.01k • 13 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 35.6k • 21 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 1.89k • 33
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 • 650 • 90 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 102 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 845 • 65 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 387 • 21
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 19.2k • 459 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 8.24k • 326 -
zai-org/cogvlm2-llama3-chat-19B
Text Generation • 20B • Updated • 3.04k • 217 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 35 • 3
-
Qwen/QwQ-32B
Text Generation • 33B • Updated • 56.2k • • 2.87k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 361k • • 732 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 2.42M • • 1.47k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • 4B • Updated • 3.18k • 254
Reinforcement Learning from Verifiable Rewards (RLVR) Datasets
-
Qwen2.5 Coder Artifacts
🐢1.7kCreate and view code for applications using text prompts
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 471k • • 878 -
Qwen/Qwen2.5-32B-Instruct
Text Generation • 33B • Updated • 304k • • 308 -
Qwen/Qwen2.5-14B-Instruct
Text Generation • 15B • Updated • 682k • • 287
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.23M • • 12.9k -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 2.42M • • 1.47k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 361k • • 732 -
allenai/Llama-3.1-Tulu-3-70B
Text Generation • 71B • Updated • 1.19k • • 61
-
HuggingFaceTB/SmolLM-135M
Text Generation • 0.1B • Updated • 417k • 234 -
HuggingFaceTB/SmolLM-135M-Instruct
Text Generation • 0.1B • Updated • 24.5k • 126 -
HuggingFaceTB/SmolLM-360M-Instruct
Text Generation • 0.4B • Updated • 10k • 83 -
HuggingFaceTB/SmolLM-360M
Text Generation • 0.4B • Updated • 19.2k • 67
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 109k • 163 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 4.01k • 13 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 35.6k • 21 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 1.89k • 33
-
Qwen/QwQ-32B
Text Generation • 33B • Updated • 56.2k • • 2.87k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 361k • • 732 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 2.42M • • 1.47k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • 4B • Updated • 3.18k • 254
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
-
Qwen2.5 Coder Artifacts
🐢1.7kCreate and view code for applications using text prompts
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 471k • • 878 -
Qwen/Qwen2.5-32B-Instruct
Text Generation • 33B • Updated • 304k • • 308 -
Qwen/Qwen2.5-14B-Instruct
Text Generation • 15B • Updated • 682k • • 287
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 1.23M • • 12.9k -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 2.42M • • 1.47k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 361k • • 732 -
allenai/Llama-3.1-Tulu-3-70B
Text Generation • 71B • Updated • 1.19k • • 61
-
MediaTek-Research/Breeze-7B-Instruct-v0_1
Text Generation • 7B • Updated • 650 • 90 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 102 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 845 • 65 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 387 • 21
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 19.2k • 459 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 8.24k • 326 -
zai-org/cogvlm2-llama3-chat-19B
Text Generation • 20B • Updated • 3.04k • 217 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 35 • 3
-
HuggingFaceTB/SmolLM-135M
Text Generation • 0.1B • Updated • 417k • 234 -
HuggingFaceTB/SmolLM-135M-Instruct
Text Generation • 0.1B • Updated • 24.5k • 126 -
HuggingFaceTB/SmolLM-360M-Instruct
Text Generation • 0.4B • Updated • 10k • 83 -
HuggingFaceTB/SmolLM-360M
Text Generation • 0.4B • Updated • 19.2k • 67