Regenerate on the Pollard master card template

README.md

@@ -23,21 +23,39 @@ tags:
 
 # MiniCPM5-2B — Pollard
 
-> ### Pollard shrank this model: **5.0 GB (f16) → 1.41 GB** — **72% smaller, 3.6× down**.
+> ### Pollard shrank this model: **5.04 GB (f16) → 1.41 GB** — **72% smaller, 3.6× down**.
 > The smallest rung here; larger, higher-fidelity rungs are listed below.
 >
 > | format | this model's size |
 > |---|---:|
-> | f16 | 5.0 GB |
-> | Q8_0 | ~2.7 GB |
-> | Q6_K | ~2.0 GB |
-> | Q4_K_M | ~1.4 GB |
+> | f16 | 5.04 GB |
+> | Q8_0 | ~2.67 GB |
+> | Q6_K | ~2.07 GB |
+> | Q4_K_M | ~1.46 GB |
 > | **PollardMix (this repo's IQ4_XS)** | **1.41 GB** |
 
 Pollard builds of [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B) made with [Pollard Weights](https://github.com/WestWaters/pollard-weights) — a ladder of **measured-allocation** quants (bits placed by per-layer sensitivity, not a uniform crush).
 
 **Standard GGUF — runs in stock llama.cpp / ik_llama.cpp, Ollama, LM Studio.** Trellis (`IQ*_KT`) files need [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp); the K-quants run anywhere.
 
+## Model details
+
+| | |
+|---|---|
+| Parameter count | ~2.5B |
+| Architecture | `llama` |
+| Input support | text |
+| imatrix | no |
+| Perplexity measured | **yes** — table below |
+
+## Which file should I choose?
+
+Every rung is the **same weights**, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context:
+
+- **~4 GB RAM / VRAM** → **`Q6_K`** (2.07 GB). Q6_K
+- **~4 GB RAM / VRAM** → **`Q5_K_M`** (1.74 GB). Q5_K_M
+- **~3 GB RAM / VRAM** → **`IQ4_XS`** (1.41 GB). IQ4_XS
+
 ## Available files
 
 | file | PPL | size | Mean KLD | notes |
@@ -46,19 +64,46 @@ Pollard builds of [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-
 | `MiniCPM5-2B-Pollard-Q5_K_M.gguf` | — | 1.74 GB | — | Q5_K_M |
 | `MiniCPM5-2B-Pollard-Q6_K.gguf` | — | 2.07 GB | — | Q6_K |
 
-_PPL / Mean-KLD benchmarking pending — sizes and allocation are final._
+## Download a specific file
+
+```bash
+pip install -U "huggingface_hub[cli]"
+hf download PollardWeights/MiniCPM5-2B-Pollard \
+  --include "MiniCPM5-2B-Pollard-IQ4_XS.gguf" --local-dir ./
+```
+
+## How to run
 
-## Usage
+These are standard GGUF and run with **llama.cpp**:
 
 ```bash
-llama-cli -m MiniCPM5-2B-Pollard-IQ4_XS.gguf -p "Explain why the sky is blue." --temp 0.7
-ollama run hf.co/PollardWeights/MiniCPM5-2B-Pollard
+llama-server -hf PollardWeights/MiniCPM5-2B-Pollard:IQ4_XS
 ```
 
+or from a local file:
+
+```bash
+llama-cli    -m MiniCPM5-2B-Pollard-IQ4_XS.gguf -ngl 99 -p "Explain why the sky is blue."
+llama-server -m MiniCPM5-2B-Pollard-IQ4_XS.gguf -ngl 99      # OpenAI-compatible API + web UI at :8080
+```
+
+They also work in anything built on llama.cpp — **LM Studio, koboldcpp, Jan, ramalama, Ollama** (`ollama run hf.co/PollardWeights/MiniCPM5-2B-Pollard`).
+
+## ARM / AVX
+
+llama.cpp repacks weights into an interleaved layout at load time for faster inference on ARM and AVX machines — no special file needed, online repacking covers these quants. The old `Q4_0_4_4/4_8/8_8` variants are not required.
+
 ## Errata
 
 - Trellis (`IQ*_KT`) quants need ik_llama.cpp to build/run; K-quants run in any recent llama.cpp.
 - Measured allocation places bits by per-layer sensitivity under a size budget.
 - Single machine; replication invited.
 
+## Credits & license
+
+- Base model: [`openbmb/MiniCPM5-2B`](https://huggingface.co/openbmb/MiniCPM5-2B)
+- Quantization tooling: [llama.cpp](https://github.com/ggml-org/llama.cpp) (ggml-org)
+- Method + tooling: [Pollard Weights](https://github.com/WestWaters/pollard-weights) — *measure first, no claim before a number.*
+- License: `apache-2.0`, inherited from the base model.
+
 *Built with [Pollard Weights](https://github.com/WestWaters/pollard-weights) — frontier models, small hardware, no compromise.*