license: other
license_name: swift-open-license-1.0
license_link: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b/blob/main/LICENSE
base_model:

• ukisai/Swift-1.5-Qwen3.8-27b
• Qwen/Qwen3.8-27B
• ajgazin/Swift-Qwen3.8-27B-Uncensored-MTP
• orcarouter/Qwen3.8-27B-Uncensored
  library_name: exllamav3
  pipeline_tag: image-text-to-text
  tags:
• exl3
• exllamav3
• qwen3_8
• swift-1.5
• abliterated
• uncensored
• reasoning
• efficient-thinking
• vision
• multimodal
• mtp
• dflash2

Swift-1.5-Qwen3.8-27B-Uncensored-EXL3-3.75bpw (SC_3.75bpw_H5_V6_MTP4)

An uncensored (abliterated), full multimodal (Vision + MTP) ExLlamaV3 (EXL3) quantization of ukisai/Swift-1.5-Qwen3.8-27b — UkisAI's second-generation GSPO (RL) and On-Policy Distillation (OPD) reasoning-efficient upgrade of Qwen/Qwen3.8-27B.

Designed specifically to run 100% inside a single 24 GB GPU (RTX 3090 / 4090) at 131,072 context alongside Qwen3.8-27B-DFlash2 block-diffusion speculative decoding (~135–155 tok/s), with the 6-bit Vision Tower and 4-bit MTP Head preserved intact.

1. Model Highlights & Architecture Summary

2. Why Swift 1.5 Over Swift 1.0 & Base Qwen3.8-27B?

UkisAI's Swift 1.5 upgrades Swift 1.0 by scaling up Group Sequence Policy Optimization (GSPO RL) and On-Policy Distillation (OPD) across multi-turn agentic and software engineering environments (ukisai/Qwen3.8-27B-multi-turn-agent-sft).

Whereas Swift 1.0 occasionally gave up early on multi-step CLI/agentic tasks when reflection tokens were penalized, Swift 1.5 distinguishes between pathological single-turn overthinking loops and legitimate multi-turn task persistence:

3. Exact Methodology & Reproduction Pipeline

All tools, refusal vectors, and quantization scripts used to produce this checkpoint are included directly in the abliteration/ directory of this repository.

Stage 1: Float32 Single-Direction Refusal Orthogonalization (131 Tensors)

Following Arditi et al. (2024) ("Refusal in Language Models Is Mediated by a Single Direction"), orcarouter/Qwen3.8-27B-Uncensored, and ajgazin/Swift-Qwen3.8-27B-Uncensored-MTP:

1. Refusal Direction Recovery (abliteration/r.pt):
   • r $\in \mathbb{R}^{5120}$ (||r||_2 = 1) is the unit-norm refusal direction extracted at Layer 38 from the mean residual-stream difference between 400 harmful (AdvBench) and 400 harmless (Alpaca) prompts, with 5 massive-activation coordinates masked to exact zero so outlier attention sinks remain unperturbed.
   • As verified by ajgazin, the cosine similarity between the Layer-38 refusal direction of Qwen/Qwen3.8-27B and UkisAI/Swift is 0.99995, confirming that UkisAI's GSPO/OPD post-training did not rotate the refusal subspace.
2. In-Place float32 Orthogonal Projection (before EXL3 quantization):
   Rather than adding a static weight delta from base Qwen3.8 (which would overwrite Swift 1.5's RL updates), we project r directly out of ukisai/Swift-1.5-Qwen3.8-27b's own weight matrices in float32 prior to saving back to bfloat16:
   • For all 130 Residual-Writing Linear Projections ($W \in \mathbb{R}^{d_{\text{model}} \times d_{\text{in}}}$):
     $$W' = W - r,(r^\top W)$$
     Applied to:
     • model.language_model.layers.{0..63}.self_attn.o_proj.weight (16 full-attention layers)
     • model.language_model.layers.{0..63}.linear_attn.out_proj.weight (48 Gated DeltaNet layers)
     • model.language_model.layers.{0..63}.mlp.down_proj.weight (64 SwiGLU MLP layers)
     • mtp.layers.0.self_attn.o_proj.weight & mtp.layers.0.mlp.down_proj.weight (2 MTP head projections — ensuring the MTP head's hidden states remain aligned with the abliterated trunk)
   • For the Token Embedding Matrix ($E \in \mathbb{R}^{248320 \times 5120}$):
     $$E' = E - (E,r),r^\top$$
     Applied to:
     • model.language_model.embed_tokens.weight (1 tensor)

Stage 2: Custom SC_3.75bpw_H5_V6_MTP4 EXL3 Quantization

Quantized from the abliterated BF16 checkpoint using ExLlamaV3 (convert.py with --override spec in abliteration/run_quantize_swift15_375.py):

• Why embed_tokens is kept in BF16 (16.00 bpw):
  • In ExLlamaV3, Embedding declares caps = {"prefer_cpu": True} and stays in pinned System RAM (0.00 GiB GPU VRAM). Benchmarking INT8 row-wise quantized embeddings showed 0 MB of GPU VRAM savings while adding +67 µs per 16-token verification step due to CPU int8 -> bf16 dequantization. Keeping embed_tokens in BF16 gives both maximum lookup speed and lossless input representations.
• Why lm_head is 5.00 bpw and model.visual.* is 6.00 bpw:
  • With a 248,320-token vocabulary, lm_head requires 5.00 bpw (SQNR = 36.27 dB) to preserve tail-token logit calibration during speculative tree verification with DFlash2.
  • All 27 Vision blocks (model.visual.blocks.0..26) and model.visual.merger are quantized to 6.00 bpw, preventing visual tokenization degradation on OCR, UI understanding, and ERQA tasks.

4. Recommended Serving Setup (ExLlamaV3 + DFlash2)

Key Serving Notes for Swift 1.5:

1. No Artificial --reasoning-budget Needed:
   • Unlike Base Qwen3.8-27B (which required --reasoning-budget 2048 to break out of infinite "Wait, let me double-check..." loops), Swift 1.5 naturally terminates <think> via its GSPO/OPD training.
   • Leave reasoning_effort="xhigh" with no hard reasoning budget cutoff (--reasoning-budget 0) so the model uses ~300–800 tokens on simple queries and dynamically scales to 4,000–8,400 tokens on complex LiveCodeBench-grade architecture/coding prompts.
2. Recommended Sampling Parameters:
   • Coding / DFlash2 Speculative Decoding: temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0.0, presence_penalty = 1.5 (applied to generated output tokens only), repetition_penalty = 1.0.
   • General Reasoning / Math Benchmarks: temperature = 1.0, top_p = 0.95, top_k = 20, min_p = 0.0.

Python Loading Example (ExLlamaV3)

from exllamav3 import Config, Model, Cache, Tokenizer, Generator

config = Config.from_directory("Swift-1.5-Qwen3.8-27B-Uncensored-EXL3-3.75bpw")
model = Model.from_config(config)
cache = Cache(model, max_num_tokens=131072) # Or CacheLayer_quant(k_bits=4, v_bits=4)
model.load()

# Optional: Load the 6-bit Vision Tower for multimodal inputs
vision_model = Model.from_config(config, component="vision")
vision_model.load()

tokenizer = Tokenizer.from_config(config)
generator = Generator(model=model, cache=cache, tokenizer=tokenizer)

5. Credits, Citations & Licenses

This model stands on the shoulders of the following open-source researchers and organizations:

1. UkisAI (ukisai/Swift-1.5-Qwen3.8-27b):
   • Post-training via GSPO (RL) and On-Policy Distillation (OPD) for -58.5% median thinking token reduction and higher agentic/coding accuracy.
   • Licensed under the Swift Open License v1.0 (free for personal, research, educational, evaluation, and commercial use for individuals and organizations up to US$1,000,000 annual gross revenue).
2. Alibaba Cloud Qwen Team (Qwen/Qwen3.8-27B):
   • Base 27B hybrid Gated DeltaNet + Full-Attention VLM architecture. Licensed under Apache License 2.0.
3. ajgazin (ajgazin/Swift-Qwen3.8-27B-Uncensored-MTP) & OrcaRouter (orcarouter/Qwen3.8-27B-Uncensored):
   • Recovery and verification of the massive-activation-masked Layer-38 refusal vector r (r.pt) and orca_tools.py projection utilities.
4. Arditi et al. (2024):
   • "Refusal in Language Models Is Mediated by a Single Direction" (arXiv:2406.11717).
5. Turboderp (ExLlamaV3):
   • EXL3 trellis quantization engine and hybrid Gated DeltaNet / VLM inference runtime.
6. z-lab (z-lab/Qwen3.8-27B-DFlash2):
   • Block-diffusion speculative decoding drafter (DFlash2) for Qwen3.8-27B.

@misc{swift-1.5-qwen3.8-27b,
  title  = {Swift 1.5 Qwen3.8-27B},
  author = {UkisAI},
  year   = {2026},
  url    = {https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b}
}

@article{arditi2024refusal,
  title   = {Refusal in Language Models Is Mediated by a Single Direction},
  author  = {Arditi, Andy and Obeso, Oscar and Syed, Aaquib and Paleka, Daniel and Panickssery, Nina and Gurnee, Wes and Nanda, Neel},
  journal = {arXiv preprint arXiv:2406.11717},
  year    = {2024}
}