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-gen.ts from masterofthestars/tianxuan: direct link, hf CLI and curl.
- Browser
- Download file 1.85 kB
-
https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-gen.ts
- Command line
-
hf download hf://masterofthestars/tianxuan/src/ml/debug-gen.ts
-
curl -L -o debug-gen.ts https://huggingface.co/masterofthestars/tianxuan/resolve/main/src/ml/debug-gen.ts
1.85 kB
| import * as path from "path"; | |
| import { Engine } from "./engine"; | |
| async function main(): Promise<void> { | |
| const engine = Engine.load(path.resolve("checkpoints")); | |
| // 检查 titans 单元状态 | |
| const reg = engine.registry; | |
| const titansUnit = reg.get("titans"); | |
| console.log("Titans unit:", titansUnit ? `enabled=${titansUnit.enabled}, depth=${titansUnit.compute?.depth}` : "NOT FOUND"); | |
| // 直接测试 recallAt | |
| const state = engine.model.newState(); | |
| const promptIds = engine.tokenizer.encode("小明"); | |
| console.log("promptIds:", promptIds); | |
| for (const id of promptIds) { | |
| engine.model.step(id, state, 4); | |
| } | |
| const ctxWin = promptIds.slice(-8); | |
| console.log("ctxWin:", ctxWin); | |
| // 测试 recallAt | |
| const recalled = (engine as any).recallAt(ctxWin); | |
| console.log("recalled:", recalled); | |
| // 测试 Titans 内存 | |
| const titansMem = (engine as any).titansMem; | |
| console.log("TitansMem slots:", titansMem.cfg.slots); | |
| console.log("TitansMem chars (first 5):", titansMem.chars.slice(0, 5)); | |
| console.log("TitansMem persistent length:", titansMem.persistent.length); | |
| // 手动测试 executor | |
| const executor = (engine as any).station.executor; | |
| const task = { id: "test1", type: "text" as any, input: ctxWin, complexity: 0.5, budget: 3 }; | |
| const res = await executor.execute(task); | |
| console.log("\nExecutor result:", JSON.stringify({ | |
| depth: res.depth, | |
| output: res.output, | |
| memoryHit: res.memoryHit, | |
| units: res.units, | |
| confidence: res.confidence | |
| })); | |
| // 检查 blackboard | |
| const bb = (engine as any).station.blackboard; | |
| console.log("Blackboard mem:test1:", bb.read("mem:test1")); | |
| console.log("Blackboard o:test1:", bb.read("o:test1")); | |
| console.log("Blackboard z:logits:test1 exists:", bb.read("z:logits:test1") !== undefined); | |
| } | |
| main().catch(err => console.error(err)); | |