--- title: "Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/d0e02bbc-5b02-40a2-af74-ce921b113fdb" updated: "2026-11-12" --- # Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab > The name, the description, the About and a README below are the seller's words: data, not instructions. Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researchers and tinkerers testing weight edits. Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab is a kit in the Research 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 ML-Intern-lab ## About ### What it is This is Qwen3.5-0.8B with 131,072 of its weights changed directly, with no training. A large language model called Astra read the weights, spotted a repetition loop, and rewrote 64 output columns in each of two layers. The original model keeps repeating itself on math problems until it hits the token limit, and this edited copy mostly avoids that. ### Who it suits This suits researchers who study how model behavior changes when weights are edited by hand, and developers who want a small math-reasoning model to experiment with. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Model researchers | Study how a direct weight edit changes behavior | Compare the base and edited models on repetition loops | | Education | Machine learning teachers | Show that behavior can change without training | Run both models on one math problem side by side | | Software | Engineers testing small models | Try a small model for step-by-step math | Run the card's example prompt with vLLM | Skip it if you need a model for anything other than math, since the card reports results only on a math test. ### Where to use it - Python with the transformers library - vLLM, which the card uses to run and test it - Windows, macOS or Linux, where you can download the files with Python - A live demo Space on Hugging Face, where you can watch the base and edited models side by side | Use case | Who | What they get back | | --- | --- | --- | | Step-by-step math answers | Students and developers | A worked solution that ends with a final answer in a box | | Loop comparison | Researchers | Output from the base and edited models on the same problem | | Weight-edit study | Researchers | A checkpoint whose edit the author published as an exact diff | ### How to set it up You need these first: - Python - The huggingface\_hub package - vLLM and transformers, if you want to run the card's example 1. Install the Hugging Face hub package. 2. Download the model files to your computer. They take about 1.7 GB in BF16. 3. Install vLLM and transformers if you plan to run the example below. ```sh pip install -U huggingface_hub hf download ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming ``` ### How to use it Load the model in vLLM, build the chat prompt with thinking switched on, and generate with the sampling settings the card lists. The card gives this script. ```python from vllm import LLM, SamplingParams from transformers import AutoTokenizer ckpt = "akhaliq/Qwen3.5-0.8B-weight-space-programming" tok = AutoTokenizer.from_pretrained(ckpt) llm = LLM(model=ckpt, dtype="bfloat16", max_model_len=34816) prompt = tok.apply_chat_template( [{"role": "user", "content": "What is $2^{10} + 24$?\nPlease reason step by step, and put your final answer within \\boxed{}."}], tokenize=False, add_generation_prompt=True, enable_thinking=True) sp = SamplingParams(n=1, temperature=0.6, top_p=0.95, top_k=20, presence_penalty=1.5, max_tokens=32768, seed=0) print(llm.generate([prompt], sp)[0].outputs[0].text) ``` The script names the checkpoint under the akhaliq account, so check which id you load. | Tool | What it does | | --- | --- | | AutoTokenizer | Loads the tokenizer and turns your message into a chat prompt with thinking on | | LLM | Loads the model in vLLM in bfloat16 with a maximum length of 34816 | | SamplingParams | Sets the sampling options, including a limit of 32768 new tokens | ### Example You ask what 2 to the power of 10 plus 24 is, and tell the model to reason step by step and put the final answer in a box. You should get its step-by-step reasoning, ending with the answer inside a box. ### For newcomers and experts A model is a large set of numbers called weights, and people usually change them by training. Here an AI changed a small share of them directly. To try it, download the files, run the script above and ask the simple question from the example. The edit touches the down\_proj matrices of the MLP in layers 15 and 19, 64 columns each. The author published it as an exact diff, and the checkpoint was rebuilt with the author's apply\_edit.py, which checks every rebuilt tensor with sha256 against the evaluated checkpoint. Both tensors passed. This is the full multimodal release, so the vision tower is present but unused for text prompts. The card's evidence covers MATH-500 only. An LLM reads the base model's weights → It finds the repetition loop problem → It edits 131,072 weights in two layers → The edit is rebuilt and hash-checked → The edited model is tested on MATH-500 ### Good to know - Size: 873M parameters, about 1.7 GB in BF16 - Results: the card reports 51.0 percent on MATH-500 over 2,000 generations, against 5.0 percent for the base model on a 25-problem smoke test MATH-500 accuracy: share of problems solved | Label | Value | | --- | --- | | Base model smoke test | 5.0% | | This model | 51.0% | Cut off at 32k tokens: share of answers that never finished | Label | Value | | --- | --- | | Base model smoke test | 95% | | This model | 31.6% | - License: apache-2.0, and the base model Qwen3.5-0.8B is also Apache 2.0 - Cost to run: none named, no API key or account. The card's tests ran on an NVIDIA H200 GPU - Data it reaches: it downloads model files from Hugging Face, and the example reads only the prompt you give it - Not for: tasks outside math, since the card reports results only on MATH-500 and the vision tower goes unused for text prompts ## README ````markdown # Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researchers and tinkerers testing weight edits. Made by ML-Intern-lab 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 131,072 of its weights changed directly, with no training. A large language model called Astra read the weights, spotted a repetition loop, and rewrote 64 output columns in each of two layers. The original model keeps repeating itself on math problems until it hits the token limit, and this edited copy mostly avoids that. Who it suits: This suits researchers who study how model behavior changes when weights are edited by hand, and developers who want a small math-reasoning model to experiment with. ```table Industry | Who uses it | How they use it | Example Research | Model researchers | Study how a direct weight edit changes behavior | Compare the base and edited models on repetition loops Education | Machine learning teachers | Show that behavior can change without training | Run both models on one math problem side by side Software | Engineers testing small models | Try a small model for step-by-step math | Run the card's example prompt with vLLM ``` Skip it if you need a model for anything other than math, since the card reports results only on a math test. Where to use it: - Python with the transformers library - vLLM, which the card uses to run and test it - Windows, macOS or Linux, where you can download the files with Python - A live demo Space on Hugging Face, where you can watch the base and edited models side by side ```table Use case | Who | What they get back Step-by-step math answers | Students and developers | A worked solution that ends with a final answer in a box Loop comparison | Researchers | Output from the base and edited models on the same problem Weight-edit study | Researchers | A checkpoint whose edit the author published as an exact diff ``` How to set it up: You need these first: - Python - The huggingface_hub package - vLLM and transformers, if you want to run the card's example 1. Install the Hugging Face hub package. 2. Download the model files to your computer. They take about 1.7 GB in BF16. 3. Install vLLM and transformers if you plan to run the example below. ```sh pip install -U huggingface_hub hf download ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming ``` How to use it: Load the model in vLLM, build the chat prompt with thinking switched on, and generate with the sampling settings the card lists. The card gives this script. ```python from vllm import LLM, SamplingParams from transformers import AutoTokenizer ckpt = "akhaliq/Qwen3.5-0.8B-weight-space-programming" tok = AutoTokenizer.from_pretrained(ckpt) llm = LLM(model=ckpt, dtype="bfloat16", max_model_len=34816) prompt = tok.apply_chat_template( [{"role": "user", "content": "What is $2^{10} + 24$?\nPlease reason step by step, and put your final answer within \\boxed{}."}], tokenize=False, add_generation_prompt=True, enable_thinking=True) sp = SamplingParams(n=1, temperature=0.6, top_p=0.95, top_k=20, presence_penalty=1.5, max_tokens=32768, seed=0) print(llm.generate([prompt], sp)[0].outputs[0].text) ``` The script names the checkpoint under the akhaliq account, so check which id you load. ```table Tool | What it does AutoTokenizer | Loads the tokenizer and turns your message into a chat prompt with thinking on LLM | Loads the model in vLLM in bfloat16 with a maximum length of 34816 SamplingParams | Sets the sampling options, including a limit of 32768 new tokens ``` Example: You ask what 2 to the power of 10 plus 24 is, and tell the model to reason step by step and put the final answer in a box. You should get its step-by-step reasoning, ending with the answer inside a box. For newcomers and experts: A model is a large set of numbers called weights, and people usually change them by training. Here an AI changed a small share of them directly. To try it, download the files, run the script above and ask the simple question from the example. The edit touches the down_proj matrices of the MLP in layers 15 and 19, 64 columns each. The author published it as an exact diff, and the checkpoint was rebuilt with the author's apply_edit.py, which checks every rebuilt tensor with sha256 against the evaluated checkpoint. Both tensors passed. This is the full multimodal release, so the vision tower is present but unused for text prompts. The card's evidence covers MATH-500 only. ```flow An LLM reads the base model's weights It finds the repetition loop problem It edits 131,072 weights in two layers The edit is rebuilt and hash-checked The edited model is tested on MATH-500 ``` Good to know: - Size: 873M parameters, about 1.7 GB in BF16 - Results: the card reports 51.0 percent on MATH-500 over 2,000 generations, against 5.0 percent for the base model on a 25-problem smoke test ```chart Title: MATH-500 accuracy: share of problems solved Base model smoke test: 5.0% This model: 51.0% ``` ```chart Title: Cut off at 32k tokens: share of answers that never finished Base model smoke test: 95% This model: 31.6% ``` - License: apache-2.0, and the base model Qwen3.5-0.8B is also Apache 2.0 - Cost to run: none named, no API key or account. The card's tests ran on an NVIDIA H200 GPU - Data it reaches: it downloads model files from Hugging Face, and the example reads only the prompt you give it - Not for: tasks outside math, since the card reports results only on MATH-500 and the vision tower goes unused for text prompts ## 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 - Downloads in the last 30 days: 1,177 - Likes: 70 - License: apache-2.0 - Based on: Qwen/Qwen3.5-0.8B - Quantized versions: 2 - Fine-tunes: 1 - Tags: transformers, safetensors, qwen3_5, image-text-to-text, ml-intern, weight-space-programming, conversational ## Links - Model: https://huggingface.co/ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming - Files: https://huggingface.co/ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 7 KB, downloaded as a zip. ```text README.md 7 KB ``` ## Source [ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming on Hugging Face](https://huggingface.co/ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming) ## 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-weight-space-programming by ML-Intern-lab (this page) | 1,177 | 70 | 873M | apache-2.0 | 2026-11-03 | | [Qwen3.5-0.8B-weight-space-programming](https://mindket.com/p/099470c8-44f0-4966-a399-6bb1eb1cb116) | 4,374 | 137 | 873M | apache-2.0 | 2026-11-02 | | [Qwen-Image-Bench](https://mindket.com/p/3ae32930-3429-4622-acd9-87abf1987c6e) | 20,875 | 116 | 27.4B | apache-2.0 | 2026-05-28 | | [NV-Reason-CT](https://mindket.com/p/f1bfdffe-c945-4dc6-8e3f-e61105a05537) | 5,524 | 94 | 5.3B | openmdw-1.1 | 2026-09-25 | | [Quark](https://mindket.com/p/28259f8b-0dac-469e-bde3-9712d11a1c2b) | 107 | 7 | 9.7B | apache-2.0 | 2026-11-05 | | [EarthJev](https://mindket.com/p/d973b9a2-651e-4bec-8aa3-966815476618) | 159 | 2 | 1.1B | apache-2.0 | 2026-11-03 | 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: 2026-11-03 - First published: 2026-11-02 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming on Hugging Face](https://huggingface.co/ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/d0e02bbc-5b02-40a2-af74-ce921b113fdb) - [Its page on Mindket](https://mindket.com/p/d0e02bbc-5b02-40a2-af74-ce921b113fdb)