base_model: Qwen/Qwen2-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
datasets:
  - path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json
    ds_type: json
    type: sharegpt
    strict: false
    conversation: chatml

  - path: data/buzz_unstacked_chosen_math_removed_filtered.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: data/capybara_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/everythinglm-data-v3_sharegpt.json
    ds_type: json
    type: sharegpt
    strict: false
    conversation: chatml

  - path: data/gpt4_data_lmys_1m_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/gpteacher-instruct-special-alpaca.json
    ds_type: json
    type: gpteacher
    conversation: chatml

  - path: data/merged_all.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: data/no_robots_sharegpt.json
    ds_type: json
    type: sharegpt
    strict: false
    conversation: chatml

  - path: data/oasst_top1_from_fusechatmixture_sharegpt.json
    ds_type: json
    type: sharegpt
    strict: false
    conversation: chatml

  - path: data/pippa_bagel_repo_3k_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/rpguild_quarter_alignment_lab_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/sharegpt_gpt4_english.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/slimorca_dedup_filtered_95k_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/soda_diaolog_longest_tenth_buzz_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/synthia-v1.3_sharegpt_12500.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/system_conversations_dolphin_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml
  
dataset_prepared_path: last_run_prepared
val_set_size: 0.002

output_dir: ./Einstein-v7-Qwen2-7B-model

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project: Einstein
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v7-Qwen2-7B

gradient_accumulation_steps: 4
micro_batch_size: 6
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00001 # look

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
   use_reentrant: true # look
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:

deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

💬 Prompt Template

You can use ChatML prompt template while using the model:

ChatML

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

This prompt template is available as a chat template, which means you can format messages using the tokenizer.apply_chat_template() method:

python

messages = [
    {"role": "system", "content": "You are helpful AI asistant."},
    {"role": "user", "content": "Hello!"}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)