Param2-17B-Thinking
BharatGen presents Param-2-17B-MoE-A2.4B, a large-scale Mixture-of-Experts (MoE) language model designed to deliver high model capacity while retaining the inference efficiency of a much smaller dense model. It uses a Hybrid MoE architecture with 17B total parameters, while activating only 2.4B parameters per token.
.png){kind=small}
About Model
* 17B parameter Mixture of Experts (MoE) language model * Multilingual: English, Hindi + 21 Indian languages * Trained on ~22 trillion tokens across two pretraining phases * Uses 64 specialized experts, dynamically activated per token * Supports long-context understanding (up to 4096 tokens) * Efficient inference: Only 2.4B active parameters per token * Advanced Capabilities: Thinking & Reasoning, Tool Calling, Mathematics, Code Generation * Designed for diverse downstream applications and further fine-tuning
Param2-17B-Thinking
Metadata
Attribution-Non-Commercial 4.0 International (CC BY-NC 4.0)
bharatgenai
Transformers
PyTorch
Open
Other
13/03/26 11:03:42
57.29 GB
Param2-17B-A2.4B-Thinking ( 2 directories )
__MACOSX
1 directories
Param2-17B-A2.4B-Thinking
20 files
Activity Overview
1
29 
25.33 GB 
837
Tags
- Mixture of Experts
- Multilingual Text
- pretrained
License Control
Attribution-Non-Commercial 4.0 International (CC BY-NC 4.0)
Version Control
Version 1(25.33 GB)
- admin·1 month(s) ago
- chevron_right
Param2-17B-A2.4B-Thinking
- chevron_right
__MACOSX
- chevron_right
Param2-17B-A2.4B-Thinking
More Models from BharatGen
- 1
- 29
- 57.29 GB
837
- 0
- 9
- 1.25 GB
- 602
- 0
- 16
- 1.62 GB
- 1,623
- 1
- 22
- 1.62 GB
- 3,284
- 0
- 21
- 1.62 GB
- 1,878
- 0
- 49
- 1.62 GB
- 2,854
- 0
- 35
- 1.62 GB
- 1,526
- 2
- 22
- 1.62 GB
- 2,981
- 0
- 11
- 1.62 GB
- 1,788
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.