Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
djtony707
/
synapse-3b
like
1
Text Generation
Safetensors
Rust
8 datasets
English
qwen2
titan-synapse
specialist-swarm
continuous-learning
merged-model
mamba
xlstm
mixture-of-experts
fast-weights
brain-inspired
local-inference
conversational
arxiv:
2306.01708
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
synapse-3b
6.18 GB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
djtony707
Upload paper/synapse_architecture.md with huggingface_hub
d814f74
verified
8 days ago
benchmarks
Add RTX 5090 benchmark results (MMLU 62.6%, GSM8K 18.9%, 106.3 tok/s)
8 days ago
paper
Upload paper/synapse_architecture.md with huggingface_hub
8 days ago
.gitattributes
1.57 kB
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
README.md
6.39 kB
Update model card with full architecture details
8 days ago
chat_template.jinja
2.51 kB
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
config.json
1.55 kB
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
generation_config.json
242 Bytes
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
model.safetensors
6.17 GB
xet
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
tokenizer.json
11.4 MB
xet
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
tokenizer_config.json
665 Bytes
Synapse-3B: TIES merge of 4 specialist adapters (math, code, general, coordinator)
8 days ago
