Ji-Xiang
Ji-Xiang
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
Text Generation Inference liked a model 1 day ago
orcarouter/OrcaSAQ-2-27B liked a dataset 4 days ago
Contrastive-LM/deepswe-clm-train-embeddings-8kOrganizations
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 209k • 210 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 2.31k • 24 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 99.1k • 57 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 3.99k • 46
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
-
meta-llama/Llama-3.2-1B
Text Generation • 1B • Updated • 800k • • 2.65k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.53M • • 2.7k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 6.19M • • 8.12k -
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 6.14k • 269
-
crusoeai/Llama-3-8B-Instruct-Gradient-1048k-GGUF
8B • Updated • 1.44k • 71 -
NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
8B • Updated • 2.28k • 165 -
ibm-granite/granite-34b-code-instruct-8k-GGUF
Text Generation • 34B • Updated • 161 • 8 -
ibm-granite/granite-20b-code-base-8k-GGUF
Text Generation • 20B • Updated • 112 • 5
-
HuggingFaceTB/SmolLM-135M
Text Generation • 0.1B • Updated • 167k • 272 -
HuggingFaceTB/SmolLM-135M-Instruct
Text Generation • 0.1B • Updated • 31.2k • 145 -
HuggingFaceTB/SmolLM-360M-Instruct
Text Generation • 0.4B • Updated • 10.9k • 89 -
HuggingFaceTB/SmolLM-360M
Text Generation • 0.4B • Updated • 12.6k • 73
-
Qwen/QwQ-32B
Text Generation • 33B • Updated • 69.1k • • 2.97k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 72.5k • • 809 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 461k • • 1.63k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • 4B • Updated • 1.34k • 285
Reinforcement Learning from Verifiable Rewards (RLVR) Datasets
-
Qwen2.5 Coder Artifacts
🐢1.73kGenerate and preview app code from a text description
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 298k • • 1k -
Qwen/Qwen2.5-32B-Instruct
Text Generation • 33B • Updated • 1.94M • • 362 -
Qwen/Qwen2.5-14B-Instruct
Text Generation • 15B • Updated • 1.81M • • 372
-
MediaTek-Research/Breeze-7B-Instruct-v0_1
Text Generation • 7B • Updated • 601 • 91 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 92 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 1.14k • 67 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 162 • 22
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 19.3k • 463 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 34.1k • 337 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 102 • 3 -
ibm-granite/granite-20b-code-base-8k-GGUF
Text Generation • 20B • Updated • 112 • 5
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 209k • 210 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 2.31k • 24 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 99.1k • 57 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 3.99k • 46
-
Qwen/QwQ-32B
Text Generation • 33B • Updated • 69.1k • • 2.97k -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 72.5k • • 809 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 461k • • 1.63k -
microsoft/Phi-4-mini-flash-reasoning
Text Generation • 4B • Updated • 1.34k • 285
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
-
meta-llama/Llama-3.2-1B
Text Generation • 1B • Updated • 800k • • 2.65k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.53M • • 2.7k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 6.19M • • 8.12k -
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 6.14k • 269
-
Qwen2.5 Coder Artifacts
🐢1.73kGenerate and preview app code from a text description
-
Qwen/Qwen2.5-72B-Instruct
Text Generation • 73B • Updated • 298k • • 1k -
Qwen/Qwen2.5-32B-Instruct
Text Generation • 33B • Updated • 1.94M • • 362 -
Qwen/Qwen2.5-14B-Instruct
Text Generation • 15B • Updated • 1.81M • • 372
-
MediaTek-Research/Breeze-7B-Instruct-v0_1
Text Generation • 7B • Updated • 601 • 91 -
MediaTek-Research/Breeze-7B-Base-v0_1
Text Generation • 7B • Updated • 92 • 23 -
MediaTek-Research/Breeze-7B-Instruct-v1_0
Text Generation • 7B • Updated • 1.14k • 67 -
YC-Chen/Breeze-7B-Instruct-v1_0-GGUF
Text Generation • 7B • Updated • 162 • 22
-
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 19.3k • 463 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 34.1k • 337 -
ibm-granite/granite-34b-code-base-8k-GGUF
Text Generation • 34B • Updated • 102 • 3 -
ibm-granite/granite-20b-code-base-8k-GGUF
Text Generation • 20B • Updated • 112 • 5
-
crusoeai/Llama-3-8B-Instruct-Gradient-1048k-GGUF
8B • Updated • 1.44k • 71 -
NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
8B • Updated • 2.28k • 165 -
ibm-granite/granite-34b-code-instruct-8k-GGUF
Text Generation • 34B • Updated • 161 • 8 -
ibm-granite/granite-20b-code-base-8k-GGUF
Text Generation • 20B • Updated • 112 • 5
-
HuggingFaceTB/SmolLM-135M
Text Generation • 0.1B • Updated • 167k • 272 -
HuggingFaceTB/SmolLM-135M-Instruct
Text Generation • 0.1B • Updated • 31.2k • 145 -
HuggingFaceTB/SmolLM-360M-Instruct
Text Generation • 0.4B • Updated • 10.9k • 89 -
HuggingFaceTB/SmolLM-360M
Text Generation • 0.4B • Updated • 12.6k • 73