EVA-Qwen2.5-72B-v0.0-FP8-Dynamic

This repo contains the copy of the original quantized to FP8. Original: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0

EVA Qwen2.5-72B v0.0

<p> A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-72B on mixture of synthetic and natural data.<br> It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.<br> </p> <p>Model is available for inference on <a href=https://featherless.ai/models/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0>Featherless.AI</a></p <p>Note: using quantized KV cache with Qwen2.5 <b>is not recommended</b> and can lead to degraded output quality. On the other hand, Qwen's KV cache is already light enough, so using f16 for it shouldn't be problematic.</p> <p>Note #2: due to some unexpected effects of data normalization, some artifacting in form of randomly appearring sequence of <code>—</code> can appear in outputs sometimes, if penalties are too high. To avoid it, ban token number <code>158</code>. Thanks to Cahvay/ALK for discovering this fix!</p> <p> <p>Prompt format is ChatML.</p><br> <h3>Recommended sampler values:</h3> <ul> <li>Temperature: 1</li> <li>Typical-P: 0.9</li> <li>Min-P: 0.05</li> <li>Top-A: 0.2</li> <li>Repetition Penalty: 1.03</li> </ul> <h3>Recommended SillyTavern presets (via CalamitousFelicitousness):</h3>

• Context
• Instruct and System Prompt

</p> <p> <br> <h3> Training data: </h3> <ul> <li>Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model's <a href=https://huggingface.co/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16>card</a> for details.</li> <li>Kalomaze's Opus_Instruct_25k dataset, filtered for refusals.</li> <li>A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe</li> <li>A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe</li> <li>Synthstruct and SynthRP datasets by Epiculous</li> </ul> <h3> Training time and hardware: </h3> <ul><li>12 hours on 8xMI300X</li></ul><br> </p> <p>Model was trained by Kearm and Auri.</p> <h4>Special thanks:</h4><ul> <li>to Gryphe, Lemmy, Kalomaze, Nopm and Epiculous for the data</li> <li>to CalamitiousFelicitousness for providing free inference for public beta testing</li> <li>and to Allura-org for support and feedback on EVA models.</li></ul> <a href=https://github.com/axolotl-ai-cloud/axolotl><img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/></a> <details><summary>See axolotl config</summary>

axolotl version: 0.4.1

base_model: Qwen/Qwen2.5-72B

load_in_8bit: false
load_in_4bit: false
strict: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: false
liger_fused_linear_cross_entropy: false

# plugins:
#   - axolotl.integrations.spectrum.SpectrumPlugin

# spectrum_top_fraction: 0.5
# # Optional if using a pre-scanned model as your base_model. Useful if using a model mirror
# spectrum_model_name: Qwen/Qwen2.5-32B

datasets:
  - path: datasets/deduped_Synthstruct-Gens_processed_sharegpt_converted_cleaned.jsonl
    type: sharegpt
  - path: datasets/opus-instruct-22k-no_refusals-filtered.jsonl
    type: sharegpt
  - path: datasets/Celeste_Filtered.jsonl
    type: sharegpt
  - path: datasets/Gryphe-S3-5-Charcards-names-2k.jsonl
    type: sharegpt
  - path: datasets/deduped_SynthRP-Gens_processed_09-25-2024-ShareGPT_converted_cleaned.jsonl
    type: sharegpt
  - path: datasets/deduped_Gryphe-4o-WP-1k.jsonl
    type: sharegpt
  - path: datasets/deduped_not_samantha_norefusals.jsonl
    type: sharegpt

chat_template: chatml
shuffle_merged_datasets: true
val_set_size: 0.001
output_dir: ./EVA-Qwen2.5-72B-SFFT-v0.0

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

# adapter: qlora
# lora_model_dir:
# lora_r: 64
# lora_alpha: 128
# lora_dropout: 0.05
# lora_target_linear: true
# peft_use_dora: true

unfrozen_parameters:
- ^lm_head.weight$
- ^model.embed_tokens.weight$
# mlp.down_proj layers
- model.layers.62.mlp.down_proj
- model.layers.64.mlp.down_proj
- model.layers.63.mlp.down_proj
- model.layers.66.mlp.down_proj
- model.layers.65.mlp.down_proj
- model.layers.67.mlp.down_proj
- model.layers.68.mlp.down_proj
- model.layers.31.mlp.down_proj
- model.layers.60.mlp.down_proj
- model.layers.69.mlp.down_proj
- model.layers.61.mlp.down_proj
- model.layers.59.mlp.down_proj
- model.layers.30.mlp.down_proj
- model.layers.70.mlp.down_proj
- model.layers.32.mlp.down_proj
- model.layers.34.mlp.down_proj
- model.layers.33.mlp.down_proj
- model.layers.76.mlp.down_proj
- model.layers.72.mlp.down_proj
- model.layers.71.mlp.down_proj
- model.layers.58.mlp.down_proj
- model.layers.75.mlp.down_proj
- model.layers.29.mlp.down_proj
- model.layers.56.mlp.down_proj
- model.layers.26.mlp.down_proj
- model.layers.35.mlp.down_proj
- model.layers.28.mlp.down_proj
- model.layers.57.mlp.down_proj
- model.layers.77.mlp.down_proj
- model.layers.36.mlp.down_proj
- model.layers.27.mlp.down_proj
- model.layers.25.mlp.down_proj
- model.layers.78.mlp.down_proj
- model.layers.37.mlp.down_proj
- model.layers.73.mlp.down_proj
- model.layers.55.mlp.down_proj
- model.layers.54.mlp.down_proj
- model.layers.74.mlp.down_proj
- model.layers.24.mlp.down_proj
- model.layers.53.mlp.down_proj
# mlp.gate_proj layers
- model.layers.78.mlp.gate_proj
- model.layers.77.mlp.gate_proj
- model.layers.76.mlp.gate_proj
- model.layers.79.mlp.gate_proj
- model.layers.75.mlp.gate_proj
- model.layers.74.mlp.gate_proj
- model.layers.73.mlp.gate_proj
- model.layers.72.mlp.gate_proj
- model.layers.71.mlp.gate_proj
- model.layers.70.mlp.gate_proj
- model.layers.69.mlp.gate_proj
- model.layers.57.mlp.gate_proj
- model.layers.54.mlp.gate_proj
- model.layers.55.mlp.gate_proj
- model.layers.68.mlp.gate_proj
- model.layers.63.mlp.gate_proj
- model.layers.53.mlp.gate_proj
- model.layers.44.mlp.gate_proj
- model.layers.45.mlp.gate_proj
- model.layers.49.mlp.gate_proj
- model.layers.58.mlp.gate_proj
- model.layers.46.mlp.gate_proj
- model.layers.56.mlp.gate_proj
- model.layers.67.mlp.gate_proj
- model.layers.62.mlp.gate_proj
- model.layers.50.mlp.gate_proj
- model.layers.64.mlp.gate_proj
- model.layers.52.mlp.gate_proj
- model.layers.40.mlp.gate_proj
- model.layers.43.mlp.gate_proj
- model.layers.48.mlp.gate_proj
- model.layers.66.mlp.gate_proj
- model.layers.47.mlp.gate_proj
- model.layers.59.mlp.gate_proj
- model.layers.65.mlp.gate_proj
- model.layers.61.mlp.gate_proj
- model.layers.60.mlp.gate_proj
- model.layers.42.mlp.gate_proj
- model.layers.51.mlp.gate_proj
- model.layers.41.mlp.gate_proj
# mlp.up_proj layers
- model.layers.70.mlp.up_proj
- model.layers.69.mlp.up_proj
- model.layers.71.mlp.up_proj
- model.layers.68.mlp.up_proj
- model.layers.72.mlp.up_proj
- model.layers.67.mlp.up_proj
- model.layers.66.mlp.up_proj
- model.layers.73.mlp.up_proj
- model.layers.46.mlp.up_proj
- model.layers.63.mlp.up_proj
- model.layers.75.mlp.up_proj
- model.layers.76.mlp.up_proj
- model.layers.74.mlp.up_proj
- model.layers.45.mlp.up_proj
- model.layers.62.mlp.up_proj
- model.layers.64.mlp.up_proj
- model.layers.65.mlp.up_proj
- model.layers.44.mlp.up_proj
- model.layers.53.mlp.up_proj
- model.layers.47.mlp.up_proj
- model.layers.49.mlp.up_proj
- model.layers.48.mlp.up_proj
- model.layers.57.mlp.up_proj
- model.layers.43.mlp.up_proj
- model.layers.42.mlp.up_proj
- model.layers.56.mlp.up_proj
- model.layers.61.mlp.up_proj
- model.layers.54.mlp.up_proj
- model.layers.40.mlp.up_proj
- model.layers.55.mlp.up_proj
- model.layers.77.mlp.up_proj
- model.layers.60.mlp.up_proj
- model.layers.41.mlp.up_proj
- model.layers.35.mlp.up_proj
- model.layers.37.mlp.up_proj
- model.layers.58.mlp.up_proj
- model.layers.34.mlp.up_proj
- model.layers.38.mlp.up_proj
- model.layers.33.mlp.up_proj
- model.layers.39.mlp.up_proj
# self_attn.k_proj layers
- model.layers.36.self_attn.k_proj
- model.layers.79.self_attn.k_proj
- model.layers.35.self_attn.k_proj
- model.layers.34.self_attn.k_proj
- model.layers.37.self_attn.k_proj
- model.layers.33.self_attn.k_proj
- model.layers.38.self_attn.k_proj
- model.layers.39.self_attn.k_proj
- model.layers.74.self_attn.k_proj
- model.layers.77.self_attn.k_proj
- model.layers.41.self_attn.k_proj
- model.layers.69.self_attn.k_proj
- model.layers.32.self_attn.k_proj
- model.layers.78.self_attn.k_proj
- model.layers.30.self_attn.k_proj
- model.layers.70.self_attn.k_proj
- model.layers.25.self_attn.k_proj
- model.layers.42.self_attn.k_proj
- model.layers.29.self_attn.k_proj
- model.layers.31.self_attn.k_proj
- model.layers.68.self_attn.k_proj
- model.layers.66.self_attn.k_proj
- model.layers.22.self_attn.k_proj
- model.layers.65.self_attn.k_proj
- model.layers.44.self_attn.k_proj
- model.layers.40.self_attn.k_proj
- model.layers.63.self_attn.k_proj
- model.layers.23.self_attn.k_proj
- model.layers.28.self_attn.k_proj
- model.layers.24.self_attn.k_proj
- model.layers.26.self_attn.k_proj
- model.layers.67.self_attn.k_proj
- model.layers.75.self_attn.k_proj
- model.layers.27.self_attn.k_proj
- model.layers.57.self_attn.k_proj
- model.layers.64.self_attn.k_proj
- model.layers.71.self_attn.k_proj
- model.layers.61.self_attn.k_proj
- model.layers.72.self_attn.k_proj
- model.layers.73.self_attn.k_proj
# self_attn.o_proj layers
- model.layers.69.self_attn.o_proj
- model.layers.39.self_attn.o_proj
- model.layers.16.self_attn.o_proj
- model.layers.14.self_attn.o_proj
- model.layers.19.self_attn.o_proj
- model.layers.42.self_attn.o_proj
- model.layers.12.self_attn.o_proj
- model.layers.15.self_attn.o_proj
- model.layers.17.self_attn.o_proj
- model.layers.38.self_attn.o_proj
- model.layers.23.self_attn.o_proj
- model.layers.22.self_attn.o_proj
- model.layers.13.self_attn.o_proj
- model.layers.29.self_attn.o_proj
- model.layers.41.self_attn.o_proj
- model.layers.44.self_attn.o_proj
- model.layers.46.self_attn.o_proj
- model.layers.45.self_attn.o_proj
- model.layers.43.self_attn.o_proj
- model.layers.49.self_attn.o_proj
- model.layers.30.self_attn.o_proj
- model.layers.26.self_attn.o_proj
- model.layers.25.self_attn.o_proj
- model.layers.37.self_attn.o_proj
- model.layers.47.self_attn.o_proj
- model.layers.11.self_attn.o_proj
- model.layers.18.self_attn.o_proj
- model.layers.28.self_attn.o_proj
- model.layers.20.self_attn.o_proj
- model.layers.27.self_attn.o_proj
- model.layers.53.self_attn.o_proj
- model.layers.52.self_attn.o_proj
- model.layers.35.self_attn.o_proj
- model.layers.71.self_attn.o_proj
- model.layers.10.self_attn.o_proj
- model.layers.3.self_attn.o_proj
- model.layers.21.self_attn.o_proj
- model.layers.24.self_attn.o_proj
- model.layers.68.self_attn.o_proj
- model.layers.48.self_attn.o_proj
# self_attn.q_proj layers
- model.layers.1.self_attn.q_proj
- model.layers.2.self_attn.q_proj
- model.layers.3.self_attn.q_proj
- model.layers.0.self_attn.q_proj
- model.layers.5.self_attn.q_proj
- model.layers.4.self_attn.q_proj
- model.layers.6.self_attn.q_proj
- model.layers.8.self_attn.q_proj
- model.layers.7.self_attn.q_proj
- model.layers.9.self_attn.q_proj
- model.layers.10.self_attn.q_proj
- model.layers.68.self_attn.q_proj
- model.layers.25.self_attn.q_proj
- model.layers.12.self_attn.q_proj
- model.layers.54.self_attn.q_proj
- model.layers.55.self_attn.q_proj
- model.layers.61.self_attn.q_proj
- model.layers.18.self_attn.q_proj
- model.layers.49.self_attn.q_proj
- model.layers.66.self_attn.q_proj
- model.layers.72.self_attn.q_proj
- model.layers.11.self_attn.q_proj
- model.layers.52.self_attn.q_proj
- model.layers.64.self_attn.q_proj
- model.layers.15.self_attn.q_proj
- model.layers.60.self_attn.q_proj
- model.layers.50.self_attn.q_proj
- model.layers.59.self_attn.q_proj
- model.layers.53.self_attn.q_proj
- model.layers.48.self_attn.q_proj
- model.layers.57.self_attn.q_proj
- model.layers.70.self_attn.q_proj
- model.layers.17.self_attn.q_proj
- model.layers.67.self_attn.q_proj
- model.layers.71.self_attn.q_proj
- model.layers.62.self_attn.q_proj
- model.layers.51.self_attn.q_proj
- model.layers.19.self_attn.q_proj
- model.layers.58.self_attn.q_proj
- model.layers.13.self_attn.q_proj
# self_attn.v_proj layers
- model.layers.23.self_attn.v_proj
- model.layers.25.self_attn.v_proj
- model.layers.26.self_attn.v_proj
- model.layers.27.self_attn.v_proj
- model.layers.28.self_attn.v_proj
- model.layers.29.self_attn.v_proj
- model.layers.30.self_attn.v_proj
- model.layers.31.self_attn.v_proj
- model.layers.34.self_attn.v_proj
- model.layers.35.self_attn.v_proj
- model.layers.36.self_attn.v_proj
- model.layers.37.self_attn.v_proj
- model.layers.38.self_attn.v_proj
- model.layers.42.self_attn.v_proj
- model.layers.48.self_attn.v_proj
- model.layers.57.self_attn.v_proj
- model.layers.58.self_attn.v_proj
- model.layers.61.self_attn.v_proj
- model.layers.63.self_attn.v_proj
- model.layers.64.self_attn.v_proj
- model.layers.65.self_attn.v_proj
- model.layers.66.self_attn.v_proj
- model.layers.69.self_attn.v_proj
- model.layers.70.self_attn.v_proj
- model.layers.74.self_attn.v_proj
- model.layers.75.self_attn.v_proj
- model.layers.72.self_attn.v_proj
- model.layers.39.self_attn.v_proj
- model.layers.41.self_attn.v_proj
- model.layers.40.self_attn.v_proj
- model.layers.33.self_attn.v_proj
- model.layers.59.self_attn.v_proj
- model.layers.16.self_attn.v_proj
- model.layers.15.self_attn.v_proj
- model.layers.76.self_attn.v_proj
- model.layers.24.self_attn.v_proj
- model.layers.68.self_attn.v_proj
- model.layers.67.self_attn.v_proj
- model.layers.55.self_attn.v_proj
- model.layers.44.self_attn.v_proj


wandb_project: EVA-Qwen2.5-72B-SFFT-v0.0
wandb_entity:
wandb_watch:
wandb_name: Unit-00
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00005
max_grad_norm: 3

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

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

warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 2
save_total_limit: 1
save_safetensors: true
hub_model_id: 
hub_strategy: 
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
# fsdp:
#   - full_shard
#   - auto_wrap
# fsdp_config:
#   fsdp_limit_all_gathers: true
#   fsdp_sync_module_states: false
#   fsdp_offload_params: true
#   fsdp_cpu_ram_efficient_loading: true
#   fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#   fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#   fsdp_activation_checkpointing: true
#   fsdp_state_dict_type: SHARDED_STATE_DICT  # Changed from FULL_STATE_DICT
#   fsdp_sharding_strategy: FULL_SHARD
#   fsdp_forward_prefetch: false  # Added
#   fsdp_backward_prefetch: "BACKWARD_PRE"  # Added
#   fsdp_backward_prefetch_limit: 1  # Added
#   fsdp_mixed_precision: BF16  # Added

</details><br>