-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper • 2603.19223 • Published • 21 -
codefuse-ai/F2LLM-v2-14B
Feature Extraction • 14B • Updated • 209 • 2 -
codefuse-ai/F2LLM-v2-8B
Feature Extraction • 8B • Updated • 105 • 3 -
codefuse-ai/F2LLM-v2-4B
Feature Extraction • 4B • Updated • 68 • 2
CodeFuse AI
community
AI & ML interests
None defined yet.
Recent Activity
Papers
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
-
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 • 24
Rodimus models developed by CodeFuse team
Native models by CodeFuse Team
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper • 2603.19223 • Published • 21 -
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper • 2512.21332 • Published • 17 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 48
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 • 186 • 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation • 33B • Updated • 102 • 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation • Updated • 10 • 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation • Updated • 23 • 26
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper • 2603.19223 • Published • 21 -
codefuse-ai/F2LLM-v2-14B
Feature Extraction • 14B • Updated • 209 • 2 -
codefuse-ai/F2LLM-v2-8B
Feature Extraction • 8B • Updated • 105 • 3 -
codefuse-ai/F2LLM-v2-4B
Feature Extraction • 4B • Updated • 68 • 2
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper • 2603.19223 • Published • 21 -
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper • 2512.21332 • Published • 17 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper • 2510.02294 • Published • 48
-
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 • 24
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 • 186 • 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation • 33B • Updated • 102 • 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation • Updated • 10 • 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation • Updated • 23 • 26
Native models by CodeFuse Team