Smilyai-labs/Mira-1-XL

mira-1-xl

mira-1-xl is a multimodal (vision + text) 27B-class model merge built on Qwen3.5-27B, blended with Claude-Opus-style reasoning distills and a Fable-style creative distill.

This repo is intended as a premium “daily driver”:

• —strong instruction following
• —improved reasoning / “thinking” behavior vs base
• —better creative tone + narrative output
• —keeps Qwen3.5’s vision capability (image+text conversations)

Not affiliated with Alibaba/Qwen, TeichAI, Jackrong, or Anthropic/Claude. “Claude / Opus / Fable” are referenced only to describe the upstream community models used as merge sources.

What’s inside

• —Architecture: Qwen3.5 multimodal (Qwen3_5ForConditionalGeneration)
• —Precision: BF16 weights
• —Modalities: image + text → text

Merge recipe (DARE-TIES)

This model is a 3-way DARE-TIES merge (drop + rescale, then weighted delta sum), with per-source sparsity (“density”) and weights.

Important: DARE-style merges are stochastic unless you fix RNG seeds. Your merge may differ slightly if you re-run.

Base

• —Qwen/Qwen3.5-27B

Merge sources + parameters

Normalization: enabled (per-tensor norm stabilization) Output dtype: bf16

Intended use

Great for:

• —multimodal Q&A (“what’s in this image?”, “summarize this screenshot”, etc.)
• —long-form writing (stories, scripts, outlines)
• —agent-style planning (multi-step task decomposition)
• —general chat + instruction following
• —“reasoning-ish” tasks where base Qwen can be too shallow

Not ideal for:

• —safety-critical domains (medical/legal/financial advice) without human review
• —guaranteed factuality (hallucinations still happen)
• —strict reproducibility (DARE merges are not deterministic unless seeded)

Usage (Transformers)

1) Quick pipeline (image-text-to-text)

from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Bc-AI/mira-1-xl")  # <- change to your repo id

messages = [
  {
    "role": "user",
    "content": [
      {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
      {"type": "text", "text": "What animal is on the candy? Answer in one sentence."}
    ]
  }
]

out = pipe(text=messages, max_new_tokens=128)
print(out)