Update README for corrected quantization (527 layers, embeddings quantized)

README.md

@@ -35,18 +35,19 @@ tokenizer needed by MLX-VLM.
 
 ## What is quantized
 
-- **525 linear layers** (`q/k/v/o` projections, MLP gate/up/down, multimodal
-  projectors) are 4-bit affine quantized: packed `uint32` `weight` (8 values per
-  word, low nibble first) + float16 `scales`/`biases`.
-- **Embeddings, layer norms, convolutions, and biases stay float16** — matching
-  MLX-VLM's standard Linear-only affine quantization. The large per-layer input
-  embedding (`embed_tokens_per_layer`) is retained at full precision, so the
-  model needs ~7 GB unified memory on Apple Silicon.
+- **527 linear and embedding layers** (`q/k/v/o` projections, MLP gate/up/down,
+  multimodal projectors, and the large embeddings) are 4-bit affine quantized:
+  packed `uint32` `weight` (8 values per word, low nibble first) + float16
+  `scales`/`biases`.
+- **Layer norms, convolutions, and biases stay float16** — matching MLX-VLM's
+  standard affine quantization. The dense per-layer input embedding
+  (`embed_tokens_per_layer`) **is** quantized here, so the package stays under
+  ~2.9 GB rather than the ~7 GB a dense embedding would force.
 
 ## Package contents
 
-- `model-00001-of-00003.safetensors` … `model-00003-of-00003.safetensors`: the
-  one 4-bit MLX model (~6.8 GB total).
+- `model-00001-of-00001.safetensors` (2,894,953,598 bytes): the 4-bit MLX model
+  in a single shard (~2.9 GB total).
 - `model.safetensors.index.json`: complete shard map.
 - `config.json` (with `quantization` + `quantization_config`), `generation_config.json`,
   `processor_config.json`, tokenizer files, and `chat_template.jinja`.
@@ -56,13 +57,13 @@ tokenizer needed by MLX-VLM.
 The conversion host has no Apple-Silicon MLX runtime, so the quantized package
 was structurally validated before upload:
 
-- 1,951 source tensors mapped with no missing or extra keys; 525 linear layers
-  quantized; embeddings left dense.
+- 1,951 source tensors mapped with no missing or extra keys; 527 linear +
+  embedding layers quantized.
 - Quantized weight format matches the MLX affine contract: 4-bit values packed
   8-per-`uint32` (low nibble first), dequantization `scale * q + bias`, group 64.
-- Round-trip dequantization of sampled layers (language + audio towers) reproduces
-  the source weights to within 4-bit precision (max absolute error ≤ ~0.015).
-- Config matches MLX-VLM `convert --quantize` output (group_size / bits / mode).
+- Round-trip dequantization of sampled layers (attention projections + the
+  2.35B-param `embed_tokens_per_layer`) reproduces the source weights to within
+  4-bit precision (max relative error ≈ 5%).
 
 **Apple-Silicon MLX-VLM inference has not been run.** Treat this as a
 structurally validated quantization pending a real Apple-Silicon text / image /