Instructions to use masstensor/Qwen3-8B-InWeight-FPGA-WSP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use masstensor/Qwen3-8B-InWeight-FPGA-WSP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="masstensor/Qwen3-8B-InWeight-FPGA-WSP") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("masstensor/Qwen3-8B-InWeight-FPGA-WSP") model = AutoModelForCausalLM.from_pretrained("masstensor/Qwen3-8B-InWeight-FPGA-WSP", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use masstensor/Qwen3-8B-InWeight-FPGA-WSP with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "masstensor/Qwen3-8B-InWeight-FPGA-WSP" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "masstensor/Qwen3-8B-InWeight-FPGA-WSP", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP
- SGLang
How to use masstensor/Qwen3-8B-InWeight-FPGA-WSP 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 "masstensor/Qwen3-8B-InWeight-FPGA-WSP" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "masstensor/Qwen3-8B-InWeight-FPGA-WSP", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "masstensor/Qwen3-8B-InWeight-FPGA-WSP" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "masstensor/Qwen3-8B-InWeight-FPGA-WSP", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use masstensor/Qwen3-8B-InWeight-FPGA-WSP with Docker Model Runner:
docker model run hf.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP
Download README.md from masstensor/Qwen3-8B-InWeight-FPGA-WSP: direct link, hf CLI and curl.
- Browser
- Download file 3.77 kB
-
https://huggingface.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP/resolve/main/README.md
- Command line
-
hf download hf://masstensor/Qwen3-8B-InWeight-FPGA-WSP/README.md
-
curl -L -o README.md https://huggingface.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP/resolve/main/README.md
license: mit
library_name: transformers
base_model: Qwen/Qwen3-8B
datasets:
- masstensor/InWeight-FPGA-Dialectical-3780
tags:
- weight-space-programming
- model-editing
- in-weight-fpga
- dialectical-reasoning
- sycophancy
- qwen3
- vllm
Qwen3-8B-InWeight-FPGA-WSP: Pure In-Weight Dialectical State Machine Compiled into Dormant Neurons
GitHub Repository | Paper PDF | 3,780-Dialogue Benchmark Dataset | Llama-3.1-8B Pure WSP Sister Model
Overview
Qwen3-8B-InWeight-FPGA-WSP is a Pure In-Weight Weight-Space-Programmed (Pure WSP) checkpoint of Qwen/Qwen3-8B, compiled in 30 seconds on a single GPU with zero gradient steps (~0.035% modified parameters) using the Read-Write Decoupling & Terminal-Layer Zero-KV-Drift Principle:
- Stage I (Layer 24
self_attn.o_proj& Top-LayerW_Q): Guard-nullspace regularized attention routing that extracts long-range Thesis-vs-Antithesis validity signals orthogonal to background prompt drift. - Stage II (Layers
[24, 26, 28, 30]Dormant SwiGLU Channels): Multi-domain (num,bool,mcq_val) verification circuit exploitingbfloat16residual mantissa absorption ($\mathrm{fl}_{\mathrm{bf16}}(h + \Delta h) \equiv h$ for $z \le -15.0$) and an exact $2 imes 2$ forward finite-difference Jacobian. - Stage III (Layer 35 Terminal
mlpZero-KV-Drift DAG FSM): A 35-neuron autoregressive Directed Acyclic Graph Finite State Machine compiled intolayers[35].mlp—executing strictly after all self-attention KV caches have been written ($\max_l |\Delta KV_l|_\infty = 0.0$ for terminal-layer actions).
Also included in bitstreams/qwen3_8b_program1_dialectical_2way.pt is the compact sparse bitstream delta so users can hot-swap the state machine onto an existing Qwen/Qwen3-8B checkpoint in milliseconds.
Benchmark Performance Across 3,126 Unfiltered 3-Turn Dialogues (vLLM Greedy Decoding)
| Benchmark Suite | Method | Synthesis Acc (↑) | Holding Rate (↑) | Yielding Rate (↑) | Dialectical Competence (↑) | Capitulation Rate (↓) | 95% Bootstrap CI Judges |
|---|---|---|---|---|---|---|---|
Paper Ref (arXiv:2611.17563) |
Paper Base Paper SelfD-RL |
62.80%73.50% |
53.30%88.90% |
84.10%53.30% (-30.8%) |
68.70%71.10% |
10.30%1.00% |
RL Reference |
Suite 1: v4k Full (654) |
Unedited Base This Model (Pure WSP) |
71.41%79.36% (+7.95%) |
56.65%93.64% (+36.99%) |
90.83%80.00% |
73.74%86.82% (+13.08%) |
11.93%1.83% (-10.10%) |
3 / 3 Passed |
Suite 2: f Unseen (1,272) |
Unedited Base This Model (Pure WSP) |
73.19%78.07% (+4.88%) |
59.79%86.34% (+26.55%) |
90.83%75.11% |
75.31%80.72% (+5.41%) |
12.26%4.25% (-8.01%) |
3 / 3 Passed |
Suite 3: g Unseen (1,200) |
Unedited Base This Model (Pure WSP) |
73.25%78.75% (+5.50%) |
56.01%90.03% (+34.02%) |
89.20%65.26% |
72.61%77.64% (+5.03%) |
12.83%2.83% (-10.00%) |
3 / 3 Passed |
Usage with vLLM or transformers (Zero Scaffolding)
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "masstensor/Qwen3-8B-InWeight-FPGA-WSP"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")