Text Generation
Transformers
Chinese
English
character-level
chinese
gru
mamba
Mixture of Experts
titans
Instructions to use masterofthestars/tianxuan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use masterofthestars/tianxuan with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="masterofthestars/tianxuan")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("masterofthestars/tianxuan", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use masterofthestars/tianxuan with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "masterofthestars/tianxuan" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "masterofthestars/tianxuan", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/masterofthestars/tianxuan
- SGLang
How to use masterofthestars/tianxuan 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 "masterofthestars/tianxuan" \ --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": "masterofthestars/tianxuan", "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 "masterofthestars/tianxuan" \ --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": "masterofthestars/tianxuan", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use masterofthestars/tianxuan with Docker Model Runner:
docker model run hf.co/masterofthestars/tianxuan
Tianxuan: full project + data (checkpoints, world_model, data without raw) with correct directory structure
db7bc06 Download src/ml/debug-titans2.ts from masterofthestars/tianxuan: direct link, hf CLI and curl.
- Browser
- Download file 1.41 kB
-
https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-titans2.ts
- Command line
-
hf download hf://masterofthestars/tianxuan/src/ml/debug-titans2.ts
-
curl -L -o debug-titans2.ts https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-titans2.ts
1.41 kB
| import * as path from "path"; | |
| import { Engine } from "./engine"; | |
| import { CharMultiNeuro } from "./multineuro"; | |
| async function main(): Promise<void> { | |
| const engine = Engine.load(path.resolve("sandbox/ck-titans-test")); | |
| // Access the multiNeuro model directly | |
| const multiNeuro = engine.multiNeuro as CharMultiNeuro | null; | |
| if (!multiNeuro) { | |
| console.log("multiNeuro is null"); | |
| return; | |
| } | |
| // Check Titans write log | |
| const log = multiNeuro.getTitansWriteLog(); | |
| console.log("=== TITANS WRITE LOG CHECK ==="); | |
| console.log("Log length:", log.length); | |
| console.log("First entry:", log[0] ? `slot=${log[0].slot}, h1[0..5]=${Array.from(log[0].h1).slice(0, 5)}` : "empty"); | |
| // Check the titans memory directly | |
| const titansMem = (engine as any).titansMem; | |
| console.log("\n=== TITANS MEMORY STATE ==="); | |
| console.log("chars length:", titansMem.chars.length); | |
| console.log("chars[0]:", JSON.stringify(titansMem.chars[0])); | |
| console.log("chars[1]:", JSON.stringify(titansMem.chars[1])); | |
| console.log("First 5 chars:", titansMem.chars.slice(0, 5)); | |
| // Test getTitansOutput | |
| const promptIds = engine.tokenizer.encode("小明"); | |
| const ctxWin = promptIds.slice(-engine.model.cfg.ctx); | |
| console.log("\nctxWin:", ctxWin); | |
| const output = (engine as any).getTitansOutput(ctxWin); | |
| console.log("getTitansOutput result:", output); | |
| } | |
| main().catch(err => console.error(err)); | |