Text Generation
MLX
English
structured-generation
parallel-decoding
constrained-decoding
apple-silicon
classification
json
Instructions to use botp/Qwen-2.5-1B-RLCD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use botp/Qwen-2.5-1B-RLCD with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("botp/Qwen-2.5-1B-RLCD") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use botp/Qwen-2.5-1B-RLCD with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "botp/Qwen-2.5-1B-RLCD" --prompt "Once upon a time"
- Atomic Chat
Download web/index.html from botp/Qwen-2.5-1B-RLCD: direct link, hf CLI and curl.
- Browser
- Download file 2.41 kB
-
https://huggingface.co/botp/Qwen-2.5-1B-RLCD/resolve/main/web/index.html
- Command line
-
hf download hf://botp/Qwen-2.5-1B-RLCD/web/index.html
-
curl -L -o index.html https://huggingface.co/botp/Qwen-2.5-1B-RLCD/resolve/main/web/index.html
2.41 kB
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Parallel Constrained vs Normal Inference (Qwen2.5 1.5B)</title> | |
| <link rel="stylesheet" href="style.css"> | |
| <link rel="preconnect" href="https://fonts.googleapis.com"> | |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> | |
| <link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500;600&family=Inter:wght@400;500;600;700&display=swap" rel="stylesheet"> | |
| </head> | |
| <body> | |
| <div class="container"> | |
| <!-- Centered Controls --> | |
| <div class="controls-bar"> | |
| <select id="preset-select" aria-label="Select Scenario Preset"></select> | |
| <button id="btn-run" class="btn-primary"> | |
| <span>⚡ Run Comparison</span> | |
| </button> | |
| </div> | |
| <!-- Speedup Summary Banner (Shows after run) --> | |
| <div id="summary-bar" class="summary-bar hidden"> | |
| <div class="summary-pill"> | |
| <span class="summary-highlight" id="sum-speedup">2.4x FASTER</span> | |
| <span class="summary-sep">·</span> | |
| <span id="sum-times">180 ms vs 435 ms</span> | |
| </div> | |
| </div> | |
| <!-- Side by Side Main View --> | |
| <main class="grid"> | |
| <!-- Left: Parallel Constrained --> | |
| <section class="card card-parallel"> | |
| <div class="card-header"> | |
| <h2>Parallel Constrained (Qwen2.5 1.5B)</h2> | |
| <span class="timer-badge badge-green" id="timer-parallel">0.0 ms</span> | |
| </div> | |
| <div class="card-body" id="body-parallel"> | |
| <pre id="parallel-output" class="code-box"><span class="placeholder-text">Click "Run Comparison" to start...</span></pre> | |
| </div> | |
| </section> | |
| <!-- Right: Normal Autoregressive --> | |
| <section class="card"> | |
| <div class="card-header"> | |
| <div class="title-with-badge"> | |
| <h2>Normal Inference (Qwen2.5 1.5B)</h2> | |
| <span id="badge-naive-hallucinated" class="badge-red hidden">0 fields hallucinated</span> | |
| </div> | |
| <span class="timer-badge" id="timer-naive">0.0 ms</span> | |
| </div> | |
| <div class="card-body" id="body-naive"> | |
| <pre id="stream-output" class="code-box"><span class="placeholder-text">Click "Run Comparison" to start...</span></pre> | |
| </div> | |
| </section> | |
| </main> | |
| </div> | |
| <script src="app.js"></script> | |
| </body> | |
| </html> | |