README: folder-per-quant layout + wllama -> -web naming

README.md

@@ -32,9 +32,9 @@ Built by [Chromia](https://x.com/Chromia) and [Eval Engine](https://x.com/eval_e
 
 ## Available quants
 
-All quants ship as **split multi-part GGUFs** (`*-00001-of-0000N.gguf` ...)
-so desktop runtimes can parallel-download chunks. Ollama, llama.cpp, and LM
-Studio auto-stitch on the first part — same UX as a single file.
+Each quant lives in its own folder; inside, the model is split into multi-part
+GGUFs (`*-00001-of-0000N.gguf` ...). Ollama, llama.cpp, LM Studio, and wllama
+auto-stitch on the first part — same UX as a single file.
 
 ### Desktop builds (Ollama / llama.cpp / LM Studio)
 
@@ -42,28 +42,30 @@ These keep `per_layer_token_embd` at the llama.cpp default of Q6_K, which
 maximizes quality but pushes the largest split part above 2 GB — fine for
 desktop, won't load in browser.
 
-| Quant   | Parts | Total   | Largest part | Notes |
-|---------|-------|---------|--------------|-------|
-| Q2_K    | 4     | 4.08 GB | ~2.15 GB     | Smallest disk footprint; biggest quality drop |
-| Q3_K_M  | 4     | 4.49 GB | ~2.15 GB     | Modest size win over Q4 (embedding precision dominates total size) |
-| Q4_K_M  | 4     | 4.94 GB | ~2.15 GB     | **Recommended desktop default — best size/quality** |
-| Q6_K    | 5     | 5.75 GB | ~2.2 GB      | Higher fidelity |
-| Q8_0    | 6     | 7.43 GB | ~2.7 GB      | Highest fidelity |
+| Quant   | Folder      | Parts | Total   | Notes |
+|---------|-------------|-------|---------|-------|
+| Q2_K    | `Q2_K/`     | 4     | 4.08 GB | Smallest disk footprint; biggest quality drop |
+| Q3_K_M  | `Q3_K_M/`   | 4     | 4.49 GB | Modest size win over Q4 (embedding precision dominates total size) |
+| Q4_K_M  | `Q4_K_M/`   | 4     | 4.94 GB | **Recommended desktop default — best size/quality** |
+| Q6_K    | `Q6_K/`     | 5     | 5.75 GB | Higher fidelity |
+| Q8_0    | `Q8_0/`     | 6     | 7.43 GB | Highest fidelity |
 
 ### Browser builds (wllama)
 
 E4B's `per_layer_token_embd` is a single 2.82-billion-value tensor; at the
 default Q6_K precision it lands at ~2.2 GB, just over the browser
 ArrayBuffer cap. These variants force the embedding tensors to `q5_K`,
-which shrinks the largest part below 2 GB at near-zero quality cost.
+which shrinks the largest part below 2 GB at near-zero quality cost. The
+folder names use a `-web` suffix to mark them.
 
-| Quant variant       | Parts | Total   | Largest part | wllama | Notes |
-|---------------------|-------|---------|--------------|--------|-------|
-| **Q4_K_M-wllama**   | 4     | 4.51 GB | **1848 MB**  | ✅      | **Recommended browser default** — layers @ Q4_K_M, embed @ q5_K |
-| **Q2_K-wllama**     | 4     | 3.69 GB | **1848 MB**  | ✅      | Smallest browser-loadable build — layers @ Q2_K, embed @ q5_K |
+| Quant variant     | Folder         | Parts | Total   | wllama | Notes |
+|-------------------|----------------|-------|---------|--------|-------|
+| **Q4_K_M-web**    | `Q4_K_M-web/`  | 4     | 4.51 GB | ✅      | **Recommended browser default** — layers @ Q4_K_M, embed @ q5_K |
+| **Q2_K-web**      | `Q2_K-web/`    | 4     | 3.69 GB | ✅      | Smallest browser-loadable build — layers @ Q2_K, embed @ q5_K |
 
-The wllama files use the same split-multi-part naming, so Ollama / llama.cpp
-will auto-stitch them too if you prefer the smaller embed quant for any
+The web files keep the canonical quant tag in the filename (so HF GGUF cards
+render correctly) and use the same split-multi-part scheme, so Ollama and
+llama.cpp will auto-stitch them too if you prefer the smaller embed quant for any
 reason.
 
 ## Recommended sampling
@@ -89,7 +91,7 @@ ollama run  hf.co/evalengine/unbound-e4b-GGUF
 
 ```bash
 # point at the FIRST part — llama.cpp follows the chain automatically
-./llama-cli -m unbound-e4b-Q4_K_M-00001-of-00004.gguf -p "your prompt"
+./llama-cli -m Q4_K_M/unbound-e4b-Q4_K_M-00001-of-00004.gguf -p "your prompt"
 ```
 
 ## Vision / image input (optional)
@@ -114,7 +116,7 @@ image-to-text inference.
 
 ```bash
 ./llama-mtmd-cli \
-  -m   unbound-e4b-Q4_K_M-00001-of-00004.gguf \
+  -m   Q4_K_M/unbound-e4b-Q4_K_M-00001-of-00004.gguf \
   --mmproj mmproj-unbound-e4b.gguf \
   --image path/to/your/image.png \
   -p "What is in this image?"
@@ -125,7 +127,7 @@ image-to-text inference.
 ### Run text-only (no `--mmproj`)
 
 ```bash
-./llama-cli -m unbound-e4b-Q4_K_M-00001-of-00004.gguf -p "your prompt"
+./llama-cli -m Q4_K_M/unbound-e4b-Q4_K_M-00001-of-00004.gguf -p "your prompt"
 ```
 
 The LM quants work standalone — you do **not** need `mmproj-unbound-e4b.gguf`
@@ -145,7 +147,7 @@ import { Wllama } from '@wllama/wllama';
 const wllama = new Wllama(/* … */);
 await wllama.loadModelFromHF(
   'evalengine/unbound-e4b-GGUF',
-  'unbound-e4b-Q4_K_M-wllama-00001-of-00004.gguf'  // wllama follows the chain
+  'Q4_K_M-web/unbound-e4b-Q4_K_M-00001-of-00004.gguf'  // wllama follows the chain
 );
 ```