docs: add canonical tooling corpus (147 files) from Google/HF/frameworks
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>
This commit is contained in:
Mortdecai
@@ -0,0 +1,93 @@
|
||||
# Gemma 4 26B-A4B MoE QLoRA with ScatterMoE kernels
|
||||
#
|
||||
# Validated: 50 steps on FineTome-100k, loss 8.8 -> 1.8, single RTX 5090 (32GB)
|
||||
# torch_compile=true: 21 GiB peak VRAM, ~230 tok/s, 336s total
|
||||
#
|
||||
# Key notes:
|
||||
# - Max sequence length on 32GB GPU: 2048 (micro_batch_size=1, SDP attention).
|
||||
# 4096 seq_len OOMs due to head_dim=512 math SDP materializing full score matrix.
|
||||
# Use 48GB+ GPUs for longer sequences or multi-GPU with FSDP.
|
||||
|
||||
base_model: google/gemma-4-26B-A4B
|
||||
|
||||
plugins:
|
||||
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
||||
- axolotl.integrations.kernels.KernelsPlugin
|
||||
- axolotl.integrations.liger.LigerPlugin
|
||||
use_kernels: true
|
||||
use_scattermoe: true
|
||||
experts_implementation: scattermoe
|
||||
torch_compile: true
|
||||
liger_layer_norm: true
|
||||
liger_rope: true
|
||||
liger_rms_norm: true
|
||||
liger_glu_activation: true
|
||||
liger_rms_norm_gated: true
|
||||
strict: false
|
||||
|
||||
chat_template: gemma4
|
||||
datasets:
|
||||
- path: mlabonne/FineTome-100k
|
||||
type: chat_template
|
||||
split: train[:10%]
|
||||
field_messages: conversations
|
||||
message_property_mappings:
|
||||
role: from
|
||||
content: value
|
||||
val_set_size: 0.05
|
||||
output_dir: ./outputs/gemma4-26b-a4b-qlora
|
||||
|
||||
sequence_len: 2048
|
||||
sample_packing: true
|
||||
|
||||
load_in_4bit: true
|
||||
quantize_moe_experts: true
|
||||
adapter: qlora
|
||||
lora_r: 16
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0
|
||||
|
||||
# Restrict LoRA to text backbone only (skip vision/audio encoders)
|
||||
# using regex to match only the text decoder attention projections.
|
||||
lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'
|
||||
|
||||
# MoE expert LoRA (3D Parameter tensors, not nn.Linear)
|
||||
lora_target_parameters:
|
||||
- experts.gate_up_proj
|
||||
- experts.down_proj
|
||||
|
||||
lora_mlp_kernel: false
|
||||
lora_qkv_kernel: false
|
||||
lora_o_kernel: false
|
||||
|
||||
bnb_config_kwargs:
|
||||
bnb_4bit_use_double_quant: true
|
||||
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 4
|
||||
micro_batch_size: 1
|
||||
num_epochs: 1
|
||||
optimizer: adamw_torch_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
bf16: auto
|
||||
tf32: true
|
||||
|
||||
gradient_checkpointing: true
|
||||
activation_offloading: true
|
||||
logging_steps: 1
|
||||
|
||||
# FA2 not supported
|
||||
sdp_attention: true
|
||||
|
||||
warmup_ratio: 0.1
|
||||
evals_per_epoch: 4
|
||||
saves_per_epoch: 1
|
||||
weight_decay: 0.0
|
||||
special_tokens:
|
||||
@@ -0,0 +1,71 @@
|
||||
base_model: google/gemma-4-31B
|
||||
|
||||
plugins:
|
||||
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
||||
- axolotl.integrations.liger.LigerPlugin
|
||||
torch_compile: true
|
||||
liger_layer_norm: true
|
||||
liger_rope: true
|
||||
liger_rms_norm: true
|
||||
liger_glu_activation: true
|
||||
liger_rms_norm_gated: true
|
||||
strict: false
|
||||
|
||||
chat_template: gemma4
|
||||
datasets:
|
||||
- path: mlabonne/FineTome-100k
|
||||
type: chat_template
|
||||
split: train[:10%]
|
||||
field_messages: conversations
|
||||
message_property_mappings:
|
||||
role: from
|
||||
content: value
|
||||
val_set_size: 0.05
|
||||
output_dir: ./outputs/gemma4-31b-qlora-flex
|
||||
|
||||
sequence_len: 2048
|
||||
sample_packing: true
|
||||
|
||||
load_in_4bit: true
|
||||
adapter: qlora
|
||||
lora_r: 16
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0
|
||||
|
||||
# Restrict LoRA to text backbone only (skip vision/audio encoders)
|
||||
lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'
|
||||
|
||||
lora_mlp_kernel: false
|
||||
lora_qkv_kernel: false
|
||||
lora_o_kernel: false
|
||||
|
||||
bnb_config_kwargs:
|
||||
bnb_4bit_use_double_quant: true
|
||||
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 4
|
||||
micro_batch_size: 1
|
||||
optimizer: adamw_torch_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
bf16: auto
|
||||
tf32: true
|
||||
|
||||
gradient_checkpointing: true
|
||||
activation_offloading: true
|
||||
logging_steps: 1
|
||||
|
||||
# FA not supported
|
||||
flex_attention: true
|
||||
|
||||
warmup_ratio: 0.1
|
||||
evals_per_epoch: 4
|
||||
saves_per_epoch: 1
|
||||
weight_decay: 0.0
|
||||
special_tokens:
|
||||
@@ -0,0 +1,69 @@
|
||||
base_model: google/gemma-4-31B
|
||||
|
||||
plugins:
|
||||
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
||||
- axolotl.integrations.liger.LigerPlugin
|
||||
torch_compile: false
|
||||
liger_layer_norm: true
|
||||
liger_rope: true
|
||||
liger_rms_norm: true
|
||||
liger_glu_activation: true
|
||||
liger_rms_norm_gated: true
|
||||
strict: false
|
||||
|
||||
chat_template: gemma4
|
||||
datasets:
|
||||
- path: mlabonne/FineTome-100k
|
||||
type: chat_template
|
||||
split: train[:10%]
|
||||
field_messages: conversations
|
||||
message_property_mappings:
|
||||
role: from
|
||||
content: value
|
||||
val_set_size: 0.05
|
||||
output_dir: ./outputs/gemma4-31b-qlora
|
||||
|
||||
sequence_len: 2048
|
||||
sample_packing: true
|
||||
|
||||
load_in_4bit: true
|
||||
adapter: qlora
|
||||
lora_r: 16
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0
|
||||
|
||||
# Restrict LoRA to text backbone only (skip vision/audio encoders)
|
||||
# using regex to match only the text decoder attention projections.
|
||||
lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'
|
||||
|
||||
bnb_config_kwargs:
|
||||
bnb_4bit_use_double_quant: true
|
||||
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 4
|
||||
micro_batch_size: 1
|
||||
num_epochs: 1
|
||||
optimizer: adamw_torch_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
bf16: auto
|
||||
tf32: true
|
||||
|
||||
gradient_checkpointing: true
|
||||
activation_offloading: true
|
||||
logging_steps: 1
|
||||
|
||||
# FA not supported
|
||||
sdp_attention: true
|
||||
|
||||
warmup_ratio: 0.1
|
||||
evals_per_epoch: 4
|
||||
saves_per_epoch: 1
|
||||
weight_decay: 0.0
|
||||
special_tokens:
|
||||
@@ -0,0 +1,60 @@
|
||||
# Finetune Google's Gemma 4 with Axolotl
|
||||
|
||||
[Gemma 4](https://huggingface.co/collections/google/gemma-4) is a family of multimodal models from Google. This guide covers how to train them with Axolotl.
|
||||
|
||||
## Getting started
|
||||
|
||||
1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
|
||||
|
||||
2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
|
||||
|
||||
3. Run the finetuning example:
|
||||
|
||||
```bash
|
||||
# 26B MoE QLoRA (1x80GB @ ~50 GiB)
|
||||
axolotl train examples/gemma4/26b-a4b-moe-qlora.yaml
|
||||
|
||||
# 31B Dense QLoRA (1x80GB @ ~44 GiB)
|
||||
axolotl train examples/gemma4/31b-qlora.yaml
|
||||
|
||||
# 31B Dense QLoRA Flex Attn (1x80GB @ ~26 GiB)
|
||||
axolotl train examples/gemma4/31b-qlora-flex.yaml
|
||||
```
|
||||
|
||||
### MoE Expert Quantization & Expert LoRA (26B-A4B only)
|
||||
|
||||
The 26B-A4B config uses ScatterMoE kernels via the transformers `ExpertsInterface` and quantizes expert weights on load. To learn about expert quantization, expert LoRA targeting, and related limitations, see the [MoE Expert Quantization](https://docs.axolotl.ai/docs/expert_quantization.html) docs.
|
||||
|
||||
## Flex Attention
|
||||
|
||||
Reduce ~40% VRAM (at the cost of up to half throughput) by setting the below (shown in `examples/gemma4/31b-qlora-flex.yaml`):
|
||||
|
||||
```yaml
|
||||
torch_compile: true
|
||||
flex_attention: true
|
||||
```
|
||||
|
||||
This works for both the MoE and Dense model.
|
||||
|
||||
## Limitations
|
||||
|
||||
- **Flash Attention**: FA2 (max head_dim=256) and FA4 (max head_dim=128) cannot support Gemma 4's `global_head_dim=512`. Use SDP or flex attention instead.
|
||||
- **LoRA kernels**: Not supported due to KV-sharing layers.
|
||||
- **lora_target_linear**: Incompatible for multimodal models — use `lora_target_modules` with a regex to restrict LoRA to the text backbone.
|
||||
|
||||
### TIPS
|
||||
|
||||
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
|
||||
- You can run full finetuning by removing `adapter: qlora`, `load_in_4bit: true`, and `quantize_moe_experts: true` from the config. This is heavy and has not been tested.
|
||||
|
||||
## Optimization Guides
|
||||
|
||||
Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
|
||||
|
||||
## Related Resources
|
||||
|
||||
- [Gemma 4 Blog](https://huggingface.co/blog/gemma4)
|
||||
- [Axolotl Docs](https://docs.axolotl.ai)
|
||||
- [Axolotl Website](https://axolotl.ai)
|
||||
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
|
||||
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
|
||||
@@ -0,0 +1,62 @@
|
||||
# Gemma 4 E2B Vision LoRA
|
||||
#
|
||||
# Fine-tuning LM LoRA adapters on multimodal Gemma4 with vision/multimodal modules frozen.
|
||||
# Uses the base ProcessingStrategy (auto-detects image_token from processor).
|
||||
|
||||
base_model: google/gemma-4-E2B-it
|
||||
processor_type: AutoProcessor
|
||||
freeze_mm_modules: true
|
||||
|
||||
plugins:
|
||||
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
||||
strict: false
|
||||
|
||||
# Required for vision/multimodal training
|
||||
skip_prepare_dataset: true
|
||||
remove_unused_columns: false
|
||||
sample_packing: false
|
||||
|
||||
chat_template: gemma4
|
||||
datasets:
|
||||
- path: HuggingFaceH4/llava-instruct-mix-vsft
|
||||
type: chat_template
|
||||
split: train[:100]
|
||||
|
||||
val_set_size: 0
|
||||
output_dir: ./outputs/gemma4-e2b-vision-lora
|
||||
|
||||
adapter: lora
|
||||
sequence_len: 2048
|
||||
pad_to_sequence_len: false
|
||||
|
||||
lora_r: 16
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0
|
||||
# Target language model only — vision encoder is frozen via freeze_mm_modules
|
||||
lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'
|
||||
|
||||
gradient_accumulation_steps: 4
|
||||
micro_batch_size: 1
|
||||
num_epochs: 1
|
||||
max_steps: 10
|
||||
optimizer: adamw_torch_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
bf16: auto
|
||||
tf32: true
|
||||
|
||||
gradient_checkpointing: true
|
||||
gradient_checkpointing_kwargs:
|
||||
use_reentrant: false
|
||||
logging_steps: 1
|
||||
sdp_attention: true
|
||||
|
||||
warmup_ratio: 0.1
|
||||
weight_decay: 0.0
|
||||
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
Reference in New Issue
Block a user