Downloads · 30 days
951
33% of all-time downloads
DarrenJiaImbue/gemma-4-e4b-it-bouncer-litertlm
gemma-4-e4b-it-bouncer-litertlm is a machine learning model from DarrenJiaImbue. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for litert-lm.
.litertlm bundle and hot-swappable LoRA adapter for the imbue-ai/bouncer-private iOS app, intended to be consumed by a forked LiteRT-LM runtime (millanatimbue/LiteRT-LM @ expose-aux-tensor-outputs).
Downloads · 30 days
951
33% of all-time downloads
All-time downloads
2.9K
Public
Repo size
99.9 GB
Likes
0
Public
Click a slice to open those files.
.litertlm56.5 GB · 100%
From the Hugging Face model README
.litertlm bundle and hot-swappable LoRA adapter for the
imbue-ai/bouncer-private
iOS app, intended to be consumed by a forked LiteRT-LM runtime
(millanatimbue/LiteRT-LM @ expose-aux-tensor-outputs).
| File | Size | Purpose |
|---|---|---|
model.litertlm | 3.9 GB | Gemma 4 E4B IT base + classifier head + LoRA tensor input slots |
lora_adapter.tflite | 18 MB | Attention-only LoRA (rank=8) hot-swapped at session creation |
tokenizer.json, tokenizer_config.json | reference copies (also embedded in model.litertlm) |
let conv = try await engine.createConversation(with: cfg)
try conv.setScopedLoraFile(loraAdapterURL) // hot-swap LoRA
try await conv.sendMessage(.text(text), // prefill + 1 decode step
optionalArgs: .init(maxOutputTokens: 1))
let logits = try conv.getAuxiliaryOutput(name: "classifier_logits")
// argmax(logits) → bucket 0 (human) ... bucket 3 (AI)
For generation (no classification), don't call setScopedLoraFile —
LoRA inputs default to zero and the model runs as base IT.
gemma4_mixed48 (Google's recommended Gemma 4 mixed
int4/int8 recipe; same family as upstream
litert-community/gemma-4-E4B-it-litert-lm)EngineConfig.maxNumTokens)google/gemma-4-E4B-it text decoder, fine-tuned with PEFT
attention-only LoRA + a 4-class NormedLinear head (LayerNorm +
Linear) over the last input token's hidden state.google-ai-edge/litert-torch with Gemma 4
classifier_head + LoRA-input wiring (see
EditLens for the
converter patches).