-
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 46 -
codefuse-ai/F2LLM-v2-8B-Preview
Feature Extraction • 8B • Updated • 19 • 3 -
codefuse-ai/F2LLM-v2-4B-Preview
Feature Extraction • 4B • Updated • 9 • 1 -
codefuse-ai/F2LLM-v2-1.7B-Preview
Feature Extraction • 2B • Updated • 8 • 2
CodeFuse AI
community
AI & ML interests
None defined yet.
Recent Activity
Papers
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
-
MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning
Paper • 2311.02303 • Published • 12 -
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
Paper • 2310.06266 • Published • 2 -
CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models
Paper • 2410.06741 • Published • 3 -
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Paper • 2503.17793 • Published • 23
Rodimus models developed by CodeFuse team
Native models by CodeFuse Team
-
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper • 2512.21332 • Published • 16 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 46 -
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
Paper • 2409.06679 • Published • 4
This is a collection of the Ling-Coder Lite open-source models and datasets.
code LLMs with extra training on 3rd party models
-
codefuse-ai/CodeFuse-CodeLlama-34B
Text Generation • 34B • Updated • 155 • 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation • 33B • Updated • 84 • 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation • Updated • 7 • 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation • Updated • 15 • 26
-
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 46 -
codefuse-ai/F2LLM-v2-8B-Preview
Feature Extraction • 8B • Updated • 19 • 3 -
codefuse-ai/F2LLM-v2-4B-Preview
Feature Extraction • 4B • Updated • 9 • 1 -
codefuse-ai/F2LLM-v2-1.7B-Preview
Feature Extraction • 2B • Updated • 8 • 2
-
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper • 2512.21332 • Published • 16 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 46 -
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
Paper • 2409.06679 • Published • 4
-
MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning
Paper • 2311.02303 • Published • 12 -
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
Paper • 2310.06266 • Published • 2 -
CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models
Paper • 2410.06741 • Published • 3 -
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Paper • 2503.17793 • Published • 23
This is a collection of the Ling-Coder Lite open-source models and datasets.
Rodimus models developed by CodeFuse team
code LLMs with extra training on 3rd party models
-
codefuse-ai/CodeFuse-CodeLlama-34B
Text Generation • 34B • Updated • 155 • 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation • 33B • Updated • 84 • 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation • Updated • 7 • 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation • Updated • 15 • 26
Native models by CodeFuse Team