Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Prannesshkva
/
Ael-Coder-16B-MoE
Like
3
Text Generation
Safetensors
English
Chinese
isom_deepseek_coder_v2
ael
ael-coder
ael-coder-16b-moe
isom
isom-r2
Mixture of Experts
mixture-of-experts
code-generation
repo-level
long-context
bounded-memory
conversational
custom_code
License:
cc-by-nc-nd-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Ael-Coder-16B-MoE
31.4 GB
Ctrl+K
Ctrl+K
1 contributor
History:
58 commits
Prannesshkva
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
99c3384
verified
3 days ago
.gitattributes
Safe
1.51 kB
feat: initial release of .gitattributes for ISOM-DeepSeek-Coder-V2-Lite
30 days ago
Ael_Coder_16B.ipynb
Safe
88.5 kB
Add verified 2.77M-token Multi-File MoE Synthesis Benchmark notebook (Ael_Coder_16B.ipynb) and update README
4 days ago
ISOM_R1_Coder_16B_Colab_Benchmark.ipynb
Safe
10.3 kB
Add interactive Google Colab benchmark notebook with 4-bit T4 & BF16 profiling
15 days ago
LICENSE
7.33 kB
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
3 days ago
NOTICE
2.59 kB
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
3 days ago
README.md
14.2 kB
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
3 days ago
config.json
Safe
2.22 kB
Rebrand to Ael Model Family (Powered by ISOM-R2 1,000,000-Token Architecture) with verified Google Colab A100 1M-token benchmarks and Ael* classes
4 days ago
configuration_isom_deepseek_coder_v2.py
10.1 kB
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
3 days ago
generation_config.json
Safe
165 Bytes
Upgrade architecture to ISOM-R2 1,000,000-Token Engine (ISOMR2VirtualSVDCache, DiskBackedPagePool, NeedleVaultBuffer, Hybrid Dense+Lexical Micro-Window Retrieval, isom_r2_engine.py)
4 days ago
isom_r2_engine.py
Safe
22.2 kB
Upgrade architecture to ISOM-R2 1,000,000-Token Engine (ISOMR2VirtualSVDCache, DiskBackedPagePool, NeedleVaultBuffer, Hybrid Dense+Lexical Micro-Window Retrieval, isom_r2_engine.py)
5 days ago
model-00001-of-000004.safetensors
8.59 GB
xet
weights: add model-00001-of-000004.safetensors (8.00 GB)
30 days ago
model-00002-of-000004.safetensors
8.59 GB
xet
weights: add model-00002-of-000004.safetensors (8.00 GB)
30 days ago
model-00003-of-000004.safetensors
8.59 GB
xet
weights: add model-00003-of-000004.safetensors (8.00 GB)
30 days ago
model-00004-of-000004.safetensors
5.64 GB
xet
weights: add model-00004-of-000004.safetensors (5.25 GB)
30 days ago
model.safetensors.index.json
480 kB
weights: add model.safetensors.index.json
30 days ago
modeling_isom_deepseek_coder_v2.py
189 kB
Add complete Dual-Layer LICENSE, Section 4 NOTICE, and upstream base_model attribution
3 days ago
tokenization_deepseek_fast.py
1.37 kB
feat: initial release of tokenization_deepseek_fast.py for ISOM-DeepSeek-Coder-V2-Lite
30 days ago
tokenizer.json
Safe
4.61 MB
feat: initial release of tokenizer.json for ISOM-DeepSeek-Coder-V2-Lite
30 days ago
tokenizer_config.json
Safe
1.32 kB
Upgrade architecture to ISOM-R2 1,000,000-Token Engine (ISOMR2VirtualSVDCache, DiskBackedPagePool, NeedleVaultBuffer, Hybrid Dense+Lexical Micro-Window Retrieval, isom_r2_engine.py)
4 days ago
