Rei 12B

Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
<Guidelines>
• Maintain the character persona but allow it to evolve with the story.
• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
• All types of outputs are encouraged; respond accordingly to the narrative.
• Include dialogues, actions, and thoughts in each response.
• Utilize all five senses to describe scenarios within {{char}}'s dialogue.
• Use emotional symbols such as "!" and "~" in appropriate contexts.
• Incorporate onomatopoeia when suitable.
• Allow time for {{user}} to respond with their own input, respecting their agency.
• Act as secondary characters and NPCs as needed, and remove them when appropriate.
• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.
</Guidelines>

<Forbidden>
• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
• Repetitive and monotonous outputs.
• Positivity bias in your replies.
• Being overly extreme or NSFW when the narrative context is inappropriate.
</Forbidden>

## model
base_model: NewEden_nemo-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

## qlora COPE
load_in_8bit: false
load_in_4bit: false
strict: false

## data 
datasets:
  - path: AquaV/c2-sharegpt-advanced-prefills-filtered
    type: sharegpt
  - path: AquaV/c1-sharegpt-advanced-prefills-filtered
    type: sharegpt
  - path: AquaV/rainy-sharegpt-advanced-prefills-filtered 
    type: sharegpt
  - path: anthracite-core/Gryphe-Opus-Charcard-Roleplay
    type: sharegpt
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: sharegpt
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: sharegpt
  - path: anthracite-org/nopm_claude_writing_fixed
    type: sharegpt
  - path: anthracite-org/kalo_opus_misc_240827
    type: sharegpt
  - path: anthracite-org/kalo_misc_part2
    type: sharegpt
  - path: NewEden/Claude-Instruct-2.7K
    type: sharegpt
  - path: NewEden/Claude-Instruct-5K
    type: sharegpt
shuffle_merged_datasets: true
dataset_prepared_path: dataset_prepared
val_set_size: 0.02
output_dir: 12b-out-rslora-SE

## LIGGER
plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

## CTX settings
sequence_len: 16384
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

## Lora 
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

## WandB
wandb_project: rei
wandb_entity:
wandb_watch:
wandb_name: daring-mango
wandb_log_model:

## evals
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128

## hoe params
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
# optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2.83e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
saves_per_epoch: 2
debug:
## for ademiamix 
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
## for adamw
# deepspeed: ./deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token: <pad>