Instructions to use vigneshwar234/TemporalMesh-Transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vigneshwar234/TemporalMesh-Transformer with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="vigneshwar234/TemporalMesh-Transformer")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vigneshwar234/TemporalMesh-Transformer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vigneshwar234/TemporalMesh-Transformer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vigneshwar234/TemporalMesh-Transformer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vigneshwar234/TemporalMesh-Transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vigneshwar234/TemporalMesh-Transformer

SGLang

How to use vigneshwar234/TemporalMesh-Transformer with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vigneshwar234/TemporalMesh-Transformer" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vigneshwar234/TemporalMesh-Transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vigneshwar234/TemporalMesh-Transformer" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vigneshwar234/TemporalMesh-Transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vigneshwar234/TemporalMesh-Transformer with Docker Model Runner:
```
docker model run hf.co/vigneshwar234/TemporalMesh-Transformer
```

vigneshwar234 commited on 18 days ago

Commit

7078228

verified ·

1 Parent(s): 2138d01

Add CHANGELOG.md

Browse files

Files changed (1) hide show

CHANGELOG.md +33 -0

CHANGELOG.md ADDED Viewed

	@@ -0,0 +1,33 @@

+# Changelog
+## [1.0.0] — 2026-05-19
+### Added
+- Initial public release of TemporalMesh Transformer (TMT)
+- `TMTConfig` — full hyperparameter dataclass with 5 model scale presets
+- `MeshBuilder` — dynamic kNN graph rebuilt every forward pass from cosine similarity
+- `MeshAttention` — multi-head attention over sparse graph edges, O(S·k) cost
+- `TemporalPositionEncoder` — RoPE + per-token learned decay scalars
+- `ExitGate` — per-token confidence scoring with freeze-on-threshold logic
+- `DualStreamFFN` — parallel syntax + semantic streams with learned gated fusion
+- `MemoryAnchorCross` — 16 persistent EMA key-value anchor vectors
+- `TMTLayer` — unified layer assembling all five components
+- `TMTModel` — full autoregressive model with tied output projection
+- `TMTOutput` — structured output dataclass (logits, exit_masks, confidences, graph_edges, memory_state, decay_scalars)
+- `TMTTrainer` — training loop with wandb logging, cosine warmup, checkpoint saving
+- `CosineWarmupScheduler` — learning rate schedule
+- `TMTLoss` — cross-entropy + 0.1 × gate auxiliary loss
+- Dataset loader for WikiText-2 and TinyStories
+- HuggingFace tokenizer wrapper
+- Full ablation notebooks (01–04)
+- 15-test pytest suite (shapes + forward pass)
+- 20-page publication-quality PDF with 7 figures and 18 equations
+- 5-subset HuggingFace benchmark dataset
+- Zenodo DOI registration
+- GitHub Pages documentation site
+### Architecture Details
+- Default: d_model=512, n_heads=8, n_layers=12, graph_k=8, exit_threshold=0.85
+- ~120M parameters (TMT-Base)
+- WikiText-2 val perplexity: 29.4 (vs 42.1 vanilla baseline)
+- Average compute per token: ~48% of full-depth baseline