90e5598930
* fix: lock version in gemma3n docs * feat: add sample configs and docs * chore: move mistraltokenizer into mistral folder * feat: update instructions * feat: add dynamic load voxtral * fix: remove incorrect vision config, add audio * fix: support voxtral processing strategy and address none in data * feat: patch mistraltokenizer subclass upstream and add missing * feat: update cce commit to include voxtral * fix: remove old comment * fix: gemma3 patch not needed anymore * fix: voxtral modeling code * fix: remove incorrect ds path * fix: adjust apply chat template parsing * feat: enable voxtral patch * fix: patch * feat: update example datasets * fix: target layer * feat: update gemma3n docs * feat: update voxtral docs * feat: revert assistant parsing to rely on new upstream changes * chore: skip test till next PR fix * fix: override upstream decode due to missing handling * feat: update readme * fix: update * feat: add magistral small think support * feat: update mistral-common dep * fix: lint * fix: remove optional dep * chore: typing * chore: simply import * feat(doc): update differences for 2507 * fix: coderrabbit comments * feat: update clarify docs on new transformers
74 lines
1.4 KiB
YAML
74 lines
1.4 KiB
YAML
base_model: mistralai/Voxtral-Mini-3B-2507
|
|
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
# Enable to use mistral-common tokenizer
|
|
tokenizer_use_mistral_common: true
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
|
|
# for use with fft to only train on language model layers
|
|
# unfrozen_parameters:
|
|
# - language_model.model.*
|
|
# - lm_head
|
|
# - embed_tokens
|
|
|
|
eot_tokens:
|
|
- <end_of_turn>
|
|
datasets:
|
|
- path: cgato/SlimOrcaDedupCleaned
|
|
type: chat_template
|
|
split: train[:1%]
|
|
field_messages: conversations
|
|
message_property_mappings:
|
|
role: from
|
|
content: value
|
|
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: qlora
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules: 'language_model.model.layers.[\d]+.(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
eval_sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: auto
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch:
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|