Implement fused modules (#747)

* MLP: Memory saving

* Remove RMSNorm restrictions

* Map packed weights to original

* FusedAttention module

* Simplify code

* Move fused modules

* Fix critical typo

* Split inplace

* Add FFT config

* Add validation of fused arguments

* Add fused arguments to config

* Update docs

* Fix validation logic

* Add fused modules to flash attn

* Only fuse during training

* Remove timing

* Formatting

* Formatting

* Formatting

* chore: lint

* chore: lint

* add e2e tests for fused llama

* no lora for tests

---------

Co-authored-by: Wing Lian <wing.lian@gmail.com>

examples/llama-2/README.md

@@ -9,12 +9,16 @@ gradient_accumulation_steps: 2
 micro_batch_size: 1
 
 ```shell
-accelerate launch scripts/finetune.py examples/llama-2/qlora.yml
-
+accelerate launch -m axolotl.cli.train examples/llama-2/qlora.yml
 ```
 or
 
 ```shell
-accelerate launch scripts/finetune.py examples/llama-2/lora.yml
-
+accelerate launch -m axolotl.cli.train examples/llama-2/lora.yml
+```
+
+To launch a full finetuning with 16-bit precision:
+
+```shell
+accelerate launch -m axolotl.cli.train examples/llama-2/fft_optimized.yml
 ```

examples/llama-2/fft_optimized.yml

@@ -0,0 +1,73 @@
+base_model: NousResearch/Llama-2-7b-hf
+base_model_config: NousResearch/Llama-2-7b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+is_llama_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: mhenrichsen/alpaca_2k_test
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: ./out
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+flash_attn_cross_entropy: false
+flash_attn_rms_norm: true
+flash_attn_fuse_qkv: false
+flash_attn_fuse_mlp: true
+
+warmup_steps: 100
+eval_steps: 0.05
+eval_table_size:
+save_steps:
+debug:
+deepspeed: #deepspeed/zero2.json # multi-gpu only
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"