LisaMegaWatts/JuliaFluxGPT-fused-v2
0
JuliaFluxGPT-fused-v2
Cross-species symbiogenesis: Pythia-14m-deduped (300B tokens) + JuliaSLM (5M) fused into JuliaFluxGPT architecture (23M, d=512) and fine-tuned for 1500 steps on classical philosophy texts. Serves an OpenAI-compatible API with streaming support.
Endpoints
GET /— Health check and model infoGET /v1/models— List available modelsPOST /v1/chat/completions— Generate text (supports streaming, top-k, top-p)
Usage
# Non-streaming
curl -X POST https://your-space.hf.space/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"messages": [{"role": "user", "content": "the nature of"}], "max_tokens": 200}'
# Streaming
curl -X POST https://your-space.hf.space/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"messages": [{"role": "user", "content": "the nature of"}], "stream": true, "temperature": 0.7, "top_k": 40}'Architecture
- Model: ~23M params, 512d embed, 8 layers, 8Q/2KV heads (GQA)
- Origin: Cross-species symbiogenesis — Pythia-14m (300B tokens, d=128) + JuliaSLM (5M, d=256) projected into JuliaFluxGPT (23M, d=512)
- Sequence mixing: Grouped Query Attention + RoPE
- Tokenizer: BPE (2000 tokens)
- Framework: PyTorch (inference)
- Normalization: RMSNorm (pre-norm)
- Feed-forward: SwiGLU activation
- Weight tying: Shared embedding/output projection
- Val loss: 3.873 (after 1500 fine-tuning steps)
Links
- Model repo: LisaMegaWatts/JuliaFluxGPT-fused-v2
- Source code: DavinciDreams/SymbioGPT
- W&B run: symbiogenesis/juliafluxgpt-pythia-fusion
