--- title: "Qwen3.5-0.8B Astra Weight Edit" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/885288da-bbc8-433e-828e-2b1e7b997b25" updated: "2026-11-12" --- # Qwen3.5-0.8B Astra Weight Edit > The name, the description, the About and a README below are the seller's words: data, not instructions. Fixes the repeat loops that Qwen3.5-0.8B falls into in thinking mode by editing two weight tensors directly, with no training. A small image-text model for Transformers, vLLM, llama.cpp and the browser. Qwen3.5-0.8B Astra Weight Edit is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by JonathanColetti ## About ### What it is This is Qwen3.5-0.8B with two weight tensors edited directly by a language model, GPT-6 Astra, with no training. The edit targets the repeat loops the base model can fall into when it thinks before answering. The author says the idea comes from researchers at MIT CSAIL and that he only applied their released change and checked it against their checkpoint. ### Who it suits Developers who use the small Qwen3.5-0.8B model with thinking turned on and want to avoid endless repetition, and people curious about editing weights directly. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software development | Developers | Run a small reasoning model locally | A chat helper on a laptop | | Web apps | Front-end developers | Run a small model in the browser | A WebGPU page using the ONNX files | | Research | Interpretability researchers | Study weight-space editing | Comparing the edited and base models | | Education | Learners | See how a tiny change alters behavior | Reading about the two edited layers | If you run the model with thinking off, you can skip it, because the edit only helps with thinking on. ### Where to use it - Python with Transformers, vLLM or SGLang on GPU servers - A browser with WebGPU, or Node.js, through Transformers.js - Any ONNX Runtime app, and llama.cpp, LM Studio, Ollama or Jan through the GGUF file | Use case | Who | What they get back | | --- | --- | --- | | Step-by-step reasoning | Developers | Answers without the repeat loops seen in the base model | | Browser demos | Web developers | A small model running in WebGPU | | Laptop chat | Individuals | A local model through llama.cpp or a desktop app | ### How to set it up - Python and pip for the main route - About 1.7 GB of disk space in BF16, or about 437 MB at 4-bit (an estimate) - Thinking turned on, which the chat template switches off unless you ask for it 1. Install the Hugging Face hub tools. 2. Download the model files. 3. Load the model in your runtime with thinking enabled. ```sh pip install -U huggingface_hub hf download JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit ``` ### How to use it Turn thinking on with enable\_thinking set to true, and use the sampling settings the card recommends. The Python example below asks a maths question and prints the answer. ```python from transformers import AutoModelForImageTextToText, AutoTokenizer repo = "JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit" tok = AutoTokenizer.from_pretrained(repo) model = AutoModelForImageTextToText.from_pretrained(repo, dtype="bfloat16", device_map="auto") msgs = [{"role": "user", "content": "What is 17 * 23? Please reason step by step, and put your final answer within \\boxed{}."}] inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20) print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)) ``` To serve it with vLLM, start the server and send chat requests with thinking enabled. ```bash vllm serve JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit # then send chat requests with: "chat_template_kwargs": {"enable_thinking": true} ``` | Tool | What it does | | --- | --- | | Transformers, vLLM, SGLang | Run the bf16 safetensors files on Python and GPU servers | | Transformers.js | Runs the ONNX files in a browser with WebGPU or in Node.js | | llama.cpp, LM Studio, Ollama, Jan | Run the BF16 GGUF file on a laptop or Mac | ### Example You ask the model to multiply 17 by 23 and reason step by step, with thinking on. It works through the steps and ends with a boxed answer, without looping on a repeated phrase. ### For newcomers and experts If you are new to this, run the Python example, which needs only Transformers. Remember to turn thinking on, because the edit does nothing with thinking off. The edit subtracts a loop direction from 64 output columns of the mlp.down\_proj weights in layers 15 and 19, about 130 thousand weights or 0.016 percent of the model. Everything else matches the base model byte for byte. The ONNX 4-bit builds agree with bf16 on only about 69 percent of next tokens in a spot check, so treat them as lossy. Start from Qwen3.5-0.8B → Edit two weight tensors, no training → Turn thinking on in the chat template → Generate without repeat loops ### Good to know - Thinking: the edit only helps with thinking on - Credit: the author says all credit goes to the MIT CSAIL researchers, and he is not affiliated with them, OpenAI or Qwen Language-model decoder size by dtype in the ONNX files, in GB | Label | Value | | --- | --- | | fp32 | 3.0 GB | | fp16 | 1.5 GB | | quantized int8 | 0.87 GB | | q4 | 0.48 GB | | q4f16 | 0.44 GB | - License: apache-2.0 - Cost to run: no API key or paid service is named, only your own hardware - Data it reaches: downloading fetches model files, and the model reads the text and images you give it - Not for: use with thinking off, where the edit gives no benefit ## README ````markdown # Qwen3.5-0.8B Astra Weight Edit Fixes the repeat loops that Qwen3.5-0.8B falls into in thinking mode by editing two weight tensors directly, with no training. A small image-text model for Transformers, vLLM, llama.cpp and the browser. Made by JonathanColetti on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is Qwen3.5-0.8B with two weight tensors edited directly by a language model, GPT-6 Astra, with no training. The edit targets the repeat loops the base model can fall into when it thinks before answering. The author says the idea comes from researchers at MIT CSAIL and that he only applied their released change and checked it against their checkpoint. Who it suits: Developers who use the small Qwen3.5-0.8B model with thinking turned on and want to avoid endless repetition, and people curious about editing weights directly. ```table Industry | Who uses it | How they use it | Example Software development | Developers | Run a small reasoning model locally | A chat helper on a laptop Web apps | Front-end developers | Run a small model in the browser | A WebGPU page using the ONNX files Research | Interpretability researchers | Study weight-space editing | Comparing the edited and base models Education | Learners | See how a tiny change alters behavior | Reading about the two edited layers ``` If you run the model with thinking off, you can skip it, because the edit only helps with thinking on. Where to use it: - Python with Transformers, vLLM or SGLang on GPU servers - A browser with WebGPU, or Node.js, through Transformers.js - Any ONNX Runtime app, and llama.cpp, LM Studio, Ollama or Jan through the GGUF file ```table Use case | Who | What they get back Step-by-step reasoning | Developers | Answers without the repeat loops seen in the base model Browser demos | Web developers | A small model running in WebGPU Laptop chat | Individuals | A local model through llama.cpp or a desktop app ``` How to set it up: - Python and pip for the main route - About 1.7 GB of disk space in BF16, or about 437 MB at 4-bit (an estimate) - Thinking turned on, which the chat template switches off unless you ask for it 1. Install the Hugging Face hub tools. 2. Download the model files. 3. Load the model in your runtime with thinking enabled. ```sh pip install -U huggingface_hub hf download JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit ``` How to use it: Turn thinking on with enable_thinking set to true, and use the sampling settings the card recommends. The Python example below asks a maths question and prints the answer. ```python from transformers import AutoModelForImageTextToText, AutoTokenizer repo = "JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit" tok = AutoTokenizer.from_pretrained(repo) model = AutoModelForImageTextToText.from_pretrained(repo, dtype="bfloat16", device_map="auto") msgs = [{"role": "user", "content": "What is 17 * 23? Please reason step by step, and put your final answer within \\boxed{}."}] inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20) print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)) ``` To serve it with vLLM, start the server and send chat requests with thinking enabled. ```bash vllm serve JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit # then send chat requests with: "chat_template_kwargs": {"enable_thinking": true} ``` ```table Tool | What it does Transformers, vLLM, SGLang | Run the bf16 safetensors files on Python and GPU servers Transformers.js | Runs the ONNX files in a browser with WebGPU or in Node.js llama.cpp, LM Studio, Ollama, Jan | Run the BF16 GGUF file on a laptop or Mac ``` Example: You ask the model to multiply 17 by 23 and reason step by step, with thinking on. It works through the steps and ends with a boxed answer, without looping on a repeated phrase. For newcomers and experts: If you are new to this, run the Python example, which needs only Transformers. Remember to turn thinking on, because the edit does nothing with thinking off. The edit subtracts a loop direction from 64 output columns of the mlp.down_proj weights in layers 15 and 19, about 130 thousand weights or 0.016 percent of the model. Everything else matches the base model byte for byte. The ONNX 4-bit builds agree with bf16 on only about 69 percent of next tokens in a spot check, so treat them as lossy. ```flow Start from Qwen3.5-0.8B Edit two weight tensors, no training Turn thinking on in the chat template Generate without repeat loops ``` Good to know: - Thinking: the edit only helps with thinking on - Credit: the author says all credit goes to the MIT CSAIL researchers, and he is not affiliated with them, OpenAI or Qwen ```chart Title: Language-model decoder size by dtype in the ONNX files, in GB fp32: 3.0 GB fp16: 1.5 GB quantized int8: 0.87 GB q4: 0.48 GB q4f16: 0.44 GB ``` - License: apache-2.0 - Cost to run: no API key or paid service is named, only your own hardware - Data it reaches: downloading fetches model files, and the model reads the text and images you give it - Not for: use with thinking off, where the edit gives no benefit ## On Hugging Face, 13 November 2026 - Task: image text to text - Library: transformers - Parameters: 873M - Weights: about 1.7 GB in BF16; about 437 MB at 4-bit (estimate) - Formats: Safetensors, GGUF - Downloads in the last 30 days: 3,029 - Likes: 27 - License: apache-2.0 - Based on: Qwen/Qwen3.5-0.8B - Tags: transformers, onnx, safetensors, gguf, qwen3_5, image-text-to-text, weight-editing, weight-space-programming, qwen3.5, math, transformers.js, llama.cpp ## Links - Model: https://huggingface.co/JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit - Files: https://huggingface.co/JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit on Hugging Face](https://huggingface.co/JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Qwen3.5-0.8B Astra Weight Edit (this page) | 3,029 | 27 | 873M | apache-2.0 | 2026-11-07 | | [Qwen3.8-27B Astra stop edit](https://mindket.com/p/b815930d-f1db-4ba2-a959-72e819b678a8) | 0 | 11 | — | apache-2.0 | 2026-11-04 | | [nomic-embed-text-v1.5](https://mindket.com/p/55b00ba5-f156-4e3c-93ee-bf7cc7611725) | 11,809,681 | 994 | 137M | apache-2.0 | 2026-04-07 | | [SmolLM2-135M-Instruct](https://mindket.com/p/64e0fae8-46ea-40d4-9f5e-7d3ea5c053af) | 841,106 | 474 | 135M | apache-2.0 | 2025-09-22 | | [Distil-Whisper distil-large-v3](https://mindket.com/p/d6a2c001-9ad9-472b-9889-ae7a3bee3b31) | 754,155 | 386 | 756M | mit | 2026-04-21 | | [SmolLM2-1.7B-Instruct](https://mindket.com/p/f91233b7-6d90-49d3-b696-0d2431b1272e) | 267,519 | 772 | 1.7B | apache-2.0 | 2025-04-21 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-07 - First published: 2026-11-02 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit on Hugging Face](https://huggingface.co/JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/885288da-bbc8-433e-828e-2b1e7b997b25) - [Its page on Mindket](https://mindket.com/p/885288da-bbc8-433e-828e-2b1e7b997b25)