-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper β’ 2603.19223 β’ Published β’ 30 -
codefuse-ai/F2LLM-v2-14B
Feature Extraction β’ 14B β’ Updated β’ 783 β’ 5 -
codefuse-ai/F2LLM-v2-8B
Feature Extraction β’ 8B β’ Updated β’ 466 β’ 3 -
codefuse-ai/F2LLM-v2-4B
Feature Extraction β’ 4B β’ Updated β’ 824 β’ 2
CodeFuse AI
community
AI & ML interests
None defined yet.
Recent Activity
View all 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 β’ 2311.02303 β’ Published β’ 12 -
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
Paper β’ 2310.06266 β’ Published β’ 2 -
CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models
Paper β’ 2410.06741 β’ Published β’ 3 -
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Paper β’ 2503.17793 β’ Published β’ 24
Rodimus models developed by CodeFuse team
Native models by CodeFuse Team
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper β’ 2603.19223 β’ Published β’ 30 -
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper β’ 2512.21332 β’ Published β’ 17 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper β’ 2510.02294 β’ Published β’ 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 β’ 34B β’ Updated β’ 569 β’ 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation β’ 33B β’ Updated β’ 521 β’ 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation β’ Updated β’ 8 β’ 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation β’ Updated β’ 21 β’ 26
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper β’ 2603.19223 β’ Published β’ 30 -
codefuse-ai/F2LLM-v2-14B
Feature Extraction β’ 14B β’ Updated β’ 783 β’ 5 -
codefuse-ai/F2LLM-v2-8B
Feature Extraction β’ 8B β’ Updated β’ 466 β’ 3 -
codefuse-ai/F2LLM-v2-4B
Feature Extraction β’ 4B β’ Updated β’ 824 β’ 2
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Paper β’ 2603.19223 β’ Published β’ 30 -
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Paper β’ 2512.21332 β’ Published β’ 17 -
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper β’ 2510.02294 β’ Published β’ 48
-
MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning
Paper β’ 2311.02303 β’ Published β’ 12 -
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
Paper β’ 2310.06266 β’ Published β’ 2 -
CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models
Paper β’ 2410.06741 β’ Published β’ 3 -
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Paper β’ 2503.17793 β’ Published β’ 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 β’ 34B β’ Updated β’ 569 β’ 93 -
codefuse-ai/CodeFuse-DeepSeek-33B
Text Generation β’ 33B β’ Updated β’ 521 β’ 62 -
codefuse-ai/CodeFuse-DeepSeek-33B-4bits
Text Generation β’ Updated β’ 8 β’ 10 -
codefuse-ai/CodeFuse-CodeLlama-34B-4bits
Text Generation β’ Updated β’ 21 β’ 26
Native models by CodeFuse Team