Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-lite-e2b-q2.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+license: gemma
+license_link: https://ai.google.dev/gemma/terms
+base_model: google/gemma-3n-E2B-it
+tags:
+  - gguf
+  - llama.cpp
+  - on-device
+  - android
+library_name: llama.cpp
+---
+
+# Gemma LITE (E2B) — a smaller dictionary, the same mind
+
+A **Model Derivative** of Google's Gemma 3n E2B, made for phones that cannot
+hold the original in memory.
+
+**Nothing about the model's reasoning was changed.** All 35 transformer blocks
+are byte-for-byte the quantisation they started as. The only modification is to
+one tensor.
+
+## What was modified
+
+`per_layer_token_embd.weight` — requantised from **q6_K to q2_K**.
+
+That single tensor is **57% of the original file**: 1,837 MiB of a 3,179 MiB
+model, shaped `[8960, 262144]`. It is a *lookup table* — one row of about 7 KB
+is read per token — and it was being stored at **higher precision than the
+layers that do the reasoning**, every one of which is q4_0.
+
+```
+llama-quantize --allow-requantize \
+  --tensor-type per_layer_token_embd=q2_K \
+  gemma-3n-E2B-it-q4_0.gguf gemma-lite-e2b-q2.gguf Q4_0
+```
+
+| | file | `per_layer_token_embd` |
+|---|---|---|
+| source (E2B q4_0) | 3.12 GiB | 1,837 MiB (q6_K) |
+| **LITE** | **2.04 GiB** | **735 MiB (q2_K)** |
+
+## Why it exists
+
+Measured on a Galaxy S22 Ultra (8 GB): the unmodified model was killed by
+Android's low-memory killer **eleven times**, never finishing load. It needs
+roughly every spare byte the phone has.
+
+Measured on a ROG Phone 8 Pro with llama.cpp and OpenCL, 8192 context:
+
+| | |
+|---|---|
+| system memory held | **~510 MiB** |
+| unevictable (anonymous) | **0.17 GiB** |
+| prompt eval | **211 tok/s** |
+| generation | **10.7 tok/s** |
+
+A ~3,800-token system prompt prefills in about **18 seconds**.
+
+## Quality
+
+Auditioned against the unmodified model — same seed, same temperature, same
+2,400-token character prompt. Both replies were in character and of comparable
+quality; the LITE build was, if anything, more faithful to the prompt's register.
+
+☠️ **This is one sample, not a benchmark.** No perplexity or standardised
+evaluation has been run. q2_K is applied to token embeddings — how the model
+represents word *meaning* — so if you need measured quality, measure it.
+
+## What it cannot do
+
+The source GGUF carries **no vision or audio encoder tensors**, so this is a
+**text-only** model. Gemma 3n's image and audio input paths are not present.
+
+## Licence
+
+Gemma 3n is provided under and subject to the **Gemma Terms of Use**:
+https://ai.google.dev/gemma/terms
+
+This is a **modified** version. The modification is described above and is
+limited to the requantisation of a single tensor. The Gemma Terms, including the
+Prohibited Use Policy, apply to this derivative and to anything derived from it.
+
+Base model: `google/gemma-3n-E2B-it`.

SHA256SUMS

@@ -0,0 +1 @@
+e1fafaaf73b424e68fe4c81e1951b43944d34f95b68fac6411981bbc16e2d702  gemma-lite-e2b-q2.gguf

gemma-lite-e2b-q2.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fafaaf73b424e68fe4c81e1951b43944d34f95b68fac6411981bbc16e2d702
+size 2193461216