Card: align metadata with the Clover quantization family

README.md

@@ -2,8 +2,28 @@
 license: mit
 library_name: llama.cpp
 base_model: Diffuspace/Clover-35B-A3B-Preview
-tags: [llama.cpp, clover, clover_moe, prebuilt, runtime, linux, cuda]
+language:
+- en
+tags:
+- llama.cpp
+- gguf
+- clover
+- clover_moe
+- prebuilt
+- runtime
+- linux
+- x86-64
+- cpu
+- cuda
+- cuda12
+- converter
+- quantize
+- imatrix
+- diffusion
+- block-diffusion
+- moe
 ---
+
 # llama.cpp with Clover support (clover_moe)
 
 **Prebuilt Clover runtime by IsValorum**
@@ -21,24 +41,51 @@ Prebuilt Linux x86_64 binaries for [Diffuspace/Clover-35B-A3B-Preview](https://h
 
 Mainline llama.cpp does not load `clover_moe`. This build adds the converter, the runtime graph and the `draft-self` speculative mode. The PR is not merged upstream; pin this repository for reproducibility.
 
-## Compatibility
+## Clover artifacts for this runtime
 
-- Model: `Diffuspace/Clover-35B-A3B-Preview` (`clover_moe`). Works with the BF16 and Q8_0 GGUFs and with third-party `clover_moe` GGUFs such as the IQ4_XS. It does not load the original safetensors.
-- Linux x86_64: the CPU package runs on any Linux; the CUDA package requires an NVIDIA GPU and CUDA 12.x runtime, with archs 80/86/89/90 (A100, H100/H200, L40S, RTX 4090, A10G). Blackwell 100/120 is not in this build.
-- Windows: no native binary here. Use WSL2 with the Linux CPU or CUDA package; a native Windows build must be compiled from the PR with CMake and MSVC. The GGUF files themselves are OS-agnostic.
-- macOS: no binary here; use a Metal build of the PR or the third-party IQ4_XS Mac build.
-- Frontends: not LM Studio or Ollama. Clover needs this `clover_moe` runtime until the PR merges upstream.
+| Artifact | Size | Link |
+|---|---|---|
+| BF16 source | 69.38 GB | [Clover-35B-A3B-Preview-BF16-GGUF](https://huggingface.co/IsValorum/Clover-35B-A3B-Preview-BF16-GGUF) |
+| Q8_0 | 36.91 GB | [Clover-35B-A3B-Preview-Q8_0-GGUF](https://huggingface.co/IsValorum/Clover-35B-A3B-Preview-Q8_0-GGUF) |
+| 1.25M I-Matrix | 383,689,280 bytes | [Clover-35B-A3B-Preview-VAL-1.25M-I-Matrix-GGUF](https://huggingface.co/IsValorum/Clover-35B-A3B-Preview-VAL-1.25M-I-Matrix-GGUF) |
+| APEX-I NanoPlus V2.1 | 12.56 GB / 11.70 GiB | [Clover-35B-A3B-Preview-APEX-I-NanoPlus-V2.1-GGUF](https://huggingface.co/IsValorum/Clover-35B-A3B-Preview-APEX-I-NanoPlus-V2.1-GGUF) |
+| APEX-I MiniPlus V2.1 | 14.75 GB / 13.74 GiB | [Clover-35B-A3B-Preview-APEX-I-MiniPlus-V2.1-GGUF](https://huggingface.co/IsValorum/Clover-35B-A3B-Preview-APEX-I-MiniPlus-V2.1-GGUF) |
+
+## Files
 
 | File | Description |
 |---|---|
-| `llama-clover-b4838ffb-linux-x64-cpu.tar.gz` | Portable CPU build |
-| `llama-clover-b4838ffb-linux-x64-cuda12.tar.gz` | CUDA build, archs `80;86;89;90` |
+| `llama-clover-b4838ffb-linux-x64-cpu.tar.gz` | Portable CPU build, `GGML_NATIVE=OFF`, runs on any x86-64 machine |
+| `llama-clover-b4838ffb-linux-x64-cuda12.tar.gz` | CUDA 12 build, archs `80;86;89;90` |
 | `llama-clover-b4838ffb-converter.tar.gz` | HF-to-GGUF converter, conversion code and gguf-py |
-| `BUILD_INFO.json` | Compiler, flags and SHA256 |
+| `BUILD_INFO.json` | Compiler, flags and SHA256 per archive |
 | `SHA256SUMS` | Checksums |
+| `config.json` | Machine-readable build descriptor used by Hub download tracking |
+
+## Compatibility
+
+- Model: `Diffuspace/Clover-35B-A3B-Preview` (`clover_moe`). Works with the BF16 and Q8_0 GGUFs and with third-party `clover_moe` GGUFs such as the IQ4_XS. It does not load the original safetensors.
+- Linux x86_64: the CPU package runs on any Linux; the CUDA package requires an NVIDIA GPU and a CUDA 12.x runtime, with archs 80/86/89/90 (A100, H100/H200, L40S, RTX 4090, A10G). Blackwell 100/120 is not in this build.
+- glibc: the Linux x64 archives require `GLIBC_2.38` or newer. Ubuntu 24.04 or equivalent is the safe baseline; older distributions need their own build from the branch.
+- Windows: no native binary here. Use WSL2 with the Linux CPU or CUDA package; a native Windows build must be compiled from the PR with CMake and MSVC. The GGUF files themselves are OS-agnostic.
+- macOS: no binary here; use a Metal build of the PR or the third-party IQ4_XS Mac build.
+- Frontends: not LM Studio or Ollama. Clover needs this `clover_moe` runtime until the PR merges upstream.
 
 ## Usage
 
+Both runtime archives are dynamically linked and ship `llama-cli`, `llama-server`, `llama-diffusion-cli`, `llama-quantize`, `llama-imatrix`, and `llama-perplexity`. Point the loader at the bundled libraries before running.
+
+CPU:
+
+```bash
+tar -xzf llama-clover-b4838ffb-linux-x64-cpu.tar.gz
+cd llama-clover-b4838ffb-linux-x64-cpu
+export LD_LIBRARY_PATH=$PWD/bin:$LD_LIBRARY_PATH
+./bin/llama-cli -m clover-bf16.gguf -c 4096 -p "Hello"
+```
+
+CUDA 12:
+
 ```bash
 tar -xzf llama-clover-b4838ffb-linux-x64-cuda12.tar.gz
 cd llama-clover-b4838ffb-linux-x64-cuda12
@@ -47,18 +94,22 @@ export LD_LIBRARY_PATH=$PWD/bin:$LD_LIBRARY_PATH
 ./bin/llama-speculative-simple -m clover-bf16.gguf --spec-type draft-self --spec-draft-n-max 15 -ctk bf16 -ctv bf16 -n 128 -c 2048 -b 256 -ub 256 -ngl 99
 ```
 
-Conversion:
+## Conversion
 
 ```bash
 tar -xzf llama-clover-b4838ffb-converter.tar.gz
 python llama-clover-converter/llama.cpp/convert_hf_to_gguf.py Diffuspace/Clover-35B-A3B-Preview --outtype bf16 --outfile clover-bf16.gguf
 ```
 
-Quantization and importance matrix:
+## Quantization and importance matrix
 
 ```bash
 ./bin/llama-quantize --allow-requantize clover-bf16.gguf clover-q8_0.gguf Q8_0
 ./bin/llama-imatrix -m clover-q8_0.gguf -f calibration.raw -o clover.imatrix.gguf --output-format gguf --process-output --no-ppl --no-escape -c 2048 -b 2048 -ub 2048 --chunks 611 -ngl 99
 ```
 
-The CUDA package requires a compatible NVIDIA driver and CUDA 12.x runtime. The CPU package is built with `GGML_NATIVE=OFF`. llama.cpp is MIT licensed; the Clover support is PR #31306 by Maphist0; the Clover weights are Apache-2.0, Copyright DiffuSpace and the Qwen team.
+The APEX-I V2.1 releases were produced with this build: `llama-quantize --imatrix imatrix-1.25M.gguf --tensor-type-file <recipe> clover-bf16.gguf <output> Q4_0 64`. The recipes carry 853 lines, including the 120 block-diffusion tensors that must stay in `F32`.
+
+## Notes
+
+The CUDA package requires a compatible NVIDIA driver and CUDA 12.x runtime. llama.cpp is MIT licensed; the Clover support is PR #31306 by Maphist0; the Clover weights are Apache-2.0, Copyright DiffuSpace and the Qwen team.