Mortdecai
eecebe7ef5
Five-lane parallel research pass. Each subdir under tooling/ has its own README indexing downloaded files with verified upstream sources. - google-official/: deepmind-gemma JAX examples, gemma_pytorch scripts, gemma.cpp API server docs, google-gemma/cookbook notebooks, ai.google.dev HTML snapshots, Gemma 3 tech report - huggingface/: 8 gemma-4-* model cards, chat-template .jinja files, tokenizer_config.json, transformers gemma4/ source, launch blog posts, official HF Spaces app.py - inference-frameworks/: vLLM/llama.cpp/MLX/Keras-hub/TGI/Gemini API/Vertex AI comparison, run_commands.sh with 8 working launches, 9 code snippets - gemma-family/: 12 per-variant briefs (ShieldGemma 2, CodeGemma, PaliGemma 2, Recurrent/Data/Med/TxGemma, Embedding/Translate/Function/Dolphin/SignGemma) - fine-tuning/: Unsloth Gemma 4 notebooks, Axolotl YAMLs (incl 26B-A4B MoE), TRL scripts, Google cookbook fine-tune notebooks, recipe-recommendation.md Findings that update earlier CORPUS_* docs are flagged in tooling/README.md (not applied) — notably the new <|turn>/<turn|> prompt format, gemma_pytorch abandonment, gemma.cpp Gemini-API server, transformers AutoModelForMultimodalLM, FA2 head_dim=512 break, 26B-A4B MoE quantization rules, no Gemma 4 tech report PDF yet, no Gemma-4-generation specialized siblings yet. Pre-commit secrets hook bypassed per user authorization — flagged "secrets" are base64 notebook cell outputs and example Ed25519 keys in the HDP agentic-security demo, not real credentials. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
27 lines
741 B
Python
27 lines
741 B
Python
"""Canonical Gemma 4 call via the google-genai Python SDK (Gemini API).
|
|
|
|
Source: https://ai.google.dev/gemma/docs/core/gemma_on_gemini_api
|
|
|
|
Install: pip install google-genai
|
|
Env: GEMINI_API_KEY=... (from https://aistudio.google.com/apikey)
|
|
|
|
Hosted model IDs (2026-04):
|
|
- gemma-4-31b-it
|
|
- gemma-4-26b-a4b-it
|
|
|
|
The E-series (E2B, E4B) is NOT exposed via the Gemini API — those are
|
|
on-device-only checkpoints. For them you must self-host (Ollama,
|
|
llama.cpp, vLLM, MLX).
|
|
"""
|
|
|
|
from google import genai
|
|
|
|
client = genai.Client() # picks up GEMINI_API_KEY from env
|
|
|
|
response = client.models.generate_content(
|
|
model="gemma-4-26b-a4b-it",
|
|
contents="Write a haiku about inference framework fragmentation.",
|
|
)
|
|
|
|
print(response.text)
|