Views
No views yet
MiniCPM-V-4.6-abliterated-MAX is an abliterated evolution built on top of openbmb/MiniCPM-V-4.6. This model applies advanced refusal direction analysis and ablation-based optimization strategies to reduce internal refusal behaviors while preserving the multimodal reasoning and instruction-following strengths of the original architecture. The result is a highly capable and ultra-efficient multimodal language model optimized for image, video, and text understanding with improved instruction adherence.
[!IMPORTANT] This model is intended for research and learning purposes only. It reduces internal refusal behaviors, and any content generated by it is used at the user’s own risk. The authors and hosting page disclaim any liability for outputs produced by this model. Users are responsible for ensuring safe, ethical, and lawful usage.
1FROM ghcr.io/ggml-org/llama.cpp:full
2
3WORKDIR /app
4
5# Install minimal dependencies required for creating a Python virtual environment
6RUN apt-get update && apt-get install -y --no-install-recommends \
7 python3-pip python3-venv \
8 && rm -rf /var/lib/apt/lists/*
9
10# Create virtual environment
11RUN python3 -m venv /opt/venv
12ENV PATH="/opt/venv/bin:$PATH"
13
14# Install Python packages inside the virtual environment only
15RUN pip install --no-cache-dir -U huggingface_hub
16
17# Download model and mmproj
18RUN python3 -c 'from huggingface_hub import hf_hub_download; \
19 repo="prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF"; \
20 hf_hub_download(repo_id=repo, filename="MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf", local_dir="/app"); \
21 hf_hub_download(repo_id=repo, filename="MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf", local_dir="/app")'
22
23CMD ["--server", \
24 "-m", "/app/MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf", \
25 "--mmproj", "/app/MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf", \
26 "--host", "0.0.0.0", \
27 "--port", "7860", \
28 "-t", "3", \
29 "--mlock", \
30 "--prio", "3", \
31 "--swa-full", \
32 "--no-slots", \
33 "-ngl", "99", \
34 "--mmap", \
35 "--log-disable", \
36 "--skip-chat-parsing", \
37 "--no-cont-batching", \
38 "--threads-http", "1", \
39 "--direct-io", \
40 "--no-repack", \
41 "--flash-attn", "off", \
42 "-c", "640000", \
43 "-n", "389012"]
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| MiniCPM-V-4.6-abliterated-MAX.BF16.gguf | BF16 | 1.52 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.F16.gguf | F16 | 1.52 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.F32.gguf | F32 | 3.02 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q2_K.gguf | Q2_K | 422 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q3_K_L.gguf | Q3_K_L | 491 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q3_K_M.gguf | Q3_K_M | 466 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q3_K_S.gguf | Q3_K_S | 435 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q4_0.gguf | Q4_0 | 501 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf | Q4_K_M | 529 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q4_K_S.gguf | Q4_K_S | 505 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q5_0.gguf | Q5_0 | 563 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q5_K_M.gguf | Q5_K_M | 578 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q5_K_S.gguf | Q5_K_S | 563 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q6_K.gguf | Q6_K | 630 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.Q8_0.gguf | Q8_0 | 812 MB | Download |
| MiniCPM-V-4.6-abliterated-MAX.mmproj-bf16.gguf | mmproj-bf16 | 1.11 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf | mmproj-f16 | 1.11 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.mmproj-f32.gguf | mmproj-f32 | 2.19 GB | Download |
| MiniCPM-V-4.6-abliterated-MAX.mmproj-q8_0.gguf | mmproj-q8_0 | 728 MB | Download |
