metadata

language:
  - en
license: other
tags:
  - axolotl
  - generated_from_trainer
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - science
  - physics
  - chemistry
  - biology
  - math
  - llama
  - llama3
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - allenai/ai2_arc
  - camel-ai/physics
  - camel-ai/chemistry
  - camel-ai/biology
  - camel-ai/math
  - metaeval/reclor
  - openbookqa
  - mandyyyyii/scibench
  - derek-thomas/ScienceQA
  - TIGER-Lab/ScienceEval
  - jondurbin/airoboros-3.2
  - LDJnr/Capybara
  - Cot-Alpaca-GPT4-From-OpenHermes-2.5
  - STEM-AI-mtl/Electrical-engineering
  - knowrohit07/saraswati-stem
  - sablo/oasst2_curated
  - lmsys/lmsys-chat-1m
  - TIGER-Lab/MathInstruct
  - bigbio/med_qa
  - meta-math/MetaMathQA-40K
  - openbookqa
  - piqa
  - metaeval/reclor
  - derek-thomas/ScienceQA
  - scibench
  - sciq
  - Open-Orca/SlimOrca
  - migtissera/Synthia-v1.3
  - TIGER-Lab/ScienceEval
  - allenai/WildChat
  - microsoft/orca-math-word-problems-200k
  - openchat/openchat_sharegpt4_dataset
  - teknium/GPTeacher-General-Instruct
  - m-a-p/CodeFeedback-Filtered-Instruction
  - totally-not-an-llm/EverythingLM-data-V3
  - HuggingFaceH4/no_robots
  - OpenAssistant/oasst_top1_2023-08-25
  - WizardLM/WizardLM_evol_instruct_70k

🔬 Einstein-v6.1-Llama3-8B

This model is a full fine-tuned version of meta-llama/Meta-Llama-3-8B on diverse datasets.

This model is finetuned using 8xRTX3090 + 1xRTXA6000 using axolotl.

This model's training was sponsored by sablo.ai.

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

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

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

  - path: data/wizardlm_evol_instruct_70k_random_half.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: data/capybara_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/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.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/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/pippa_bagel_repo_3k_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml  

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

  - path: data/sharegpt_gpt4_english.json
    ds_type: json
    type: sharegpt
    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/everythinglm-data-v3_sharegpt.json
    ds_type: json
    type: sharegpt
    strict: false
    conversation: chatml

dataset_prepared_path: last_run_prepared
val_set_size: 0.002

output_dir: ./Einstein-v6.1-Llama3-8B-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: Einstein-v6.1-Llama3-2-epoch
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v6.1-Llama3-8B

save_safetensors: true

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit # look
lr_scheduler: cosine
learning_rate: 0.000005 # look

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

warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 2
debug:

deepspeed: zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  unk_token: "<unk>"
  pad_token: <|end_of_text|> # changed
tokens:
  - "<|im_start|>"

💬 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:

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)