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-gen2.ts from masterofthestars/tianxuan: direct link, hf CLI and curl.
- Browser
- Download file 1.66 kB
-
https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-gen2.ts
- Command line
-
hf download hf://masterofthestars/tianxuan/src/ml/debug-gen2.ts
-
curl -L -o debug-gen2.ts https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-gen2.ts
1.66 kB
| import * as path from "path"; | |
| import { Engine } from "./engine"; | |
| async function main(): Promise<void> { | |
| const engine = Engine.load(path.resolve("sandbox/ck-full-multi")); | |
| // 直接测试 Titans 记忆 | |
| const titansMem = (engine as any).titansMem; | |
| console.log("TitansMem slots:", titansMem.cfg.slots); | |
| console.log("TitansMem chars (first 10):", titansMem.chars.slice(0, 10)); | |
| console.log("TitansMem occupancy:", titansMem.occupancy().toFixed(2)); | |
| // 测试 recallAt | |
| const promptIds = engine.tokenizer.encode("小明"); | |
| const ctxWin = promptIds.slice(-engine.model.cfg.ctx); | |
| console.log("ctxWin:", ctxWin); | |
| const q = Float64Array.from(engine.model.embedAvg(ctxWin)); | |
| const cache = { query: new Float64Array(0), keys: new Float64Array(0), values: new Float64Array(0), weights: new Float64Array(0) }; | |
| const mem = titansMem.read(q, cache); | |
| console.log("hitSlots:", mem.hitSlots); | |
| console.log("weights (first 10):", cache.weights.slice(0, 10)); | |
| // 找到权重最大的槽位 | |
| let best = 0; | |
| for (let i = 1; i < cache.weights.length; i++) { | |
| if (cache.weights[i] > cache.weights[best]) best = i; | |
| } | |
| console.log("best slot:", best, "weight:", cache.weights[best]); | |
| console.log("chars[best]:", titansMem.chars[best]); | |
| console.log("chars[best % slots]:", titansMem.chars[best % titansMem.cfg.slots]); | |
| // 测试生成 | |
| const res = await engine.generate({ prompt: "小明", maxLen: 20, budget: 3, temperature: 0.85, topK: 5 }); | |
| console.log("\n生成结果:", res.text); | |
| console.log("路由统计:", res.routes.map(r => `L${r.depth}:${r.char}`).join("")); | |
| } | |
| main().catch(err => console.error(err)); | |