🔬 Einstein-v7-Qwen2-7B-GGUF

Name: Einstein-v7-Qwen2-7B-GGUF
Availability: InStock

This is quantized version of Weyaxi/Einstein-v7-Qwen2-7B created using llama.cpp

Model Description

This model is a full fine-tuned version of Qwen/Qwen2-7B on diverse datasets.

This model is finetuned using 8xMI300X using axolotl.

See axolotl config

axolotl version: 0.4.0

yaml

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)

📊 Datasets used in this model

The datasets used to train this model are listed in the metadata section of the model card.

Please note that certain datasets mentioned in the metadata may have undergone filtering based on various criteria.

The results of this filtering process and its outcomes are in a diffrent repository:

Weyaxi/sci-datasets/main

🎯 Open LLM Leaderboard Evaluation Results

🤖 Additional information about training

This model is full fine-tuned for 2 epoch.

Total number of steps was 500.

Loss graph

QuantFactory/Einstein-v7-Qwen2-7B-GGUF