|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: EVA-Qwen2.5-32B-SFFT-v0.0 |
|
results: [] |
|
quantized_by: SvdH |
|
base_model_relation: quantized |
|
--- |
|
|
|
# EVA Qwen2.5-32B v0.0 |
|
|
|
6BPW ExLLamaV2 quant of https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.0 |
|
|
|
Using parquet: https://huggingface.co/datasets/roleplay4fun/pippa |
|
|
|
<p> |
|
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B 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>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> |
|
<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](https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1/blob/main/%5BChatML%5D%20Roleplay-v1.9%20Context.json) |
|
- [Instruct and System Prompt](https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1/blob/main/%5BChatML%5D%20Roleplay-v1.9%20Instruct.json) |
|
</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>7 hours on 8xH100 SXM, provided by <a href=https://featherless.ai/>FeatherlessAI</a></li></ul><br> |
|
</p> |
|
<p>Model was trained by Kearm and Auri.</p> |
|
<h4>Special thanks:</h4><ul> |
|
<li><b>to <a href=https://featherless.ai/>FeatherlessAI</a> for generously providing 8xH100 SXM node for training of this model</b></li> |
|
<li>to Gryphe, Lemmy, Kalomaze, Nopm and Epiculous for the data</li> |
|
<li>and to Allura-org for support and feedback on EVA models.</li></ul> |
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.1` |
|
```yaml |
|
base_model: Qwen/Qwen2.5-32B |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
# 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-Qwen2.5-32B-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: 64 |
|
# lora_dropout: 0.05 |
|
# lora_target_linear: true |
|
# peft_use_dora: true |
|
|
|
unfrozen_parameters: |
|
- ^lm_head.weight$ |
|
- ^model.embed_tokens.weight$ |
|
# input_layernorm layers |
|
- model.layers.0.input_layernorm |
|
- model.layers.1.input_layernorm |
|
- model.layers.2.input_layernorm |
|
- model.layers.3.input_layernorm |
|
- model.layers.4.input_layernorm |
|
- model.layers.5.input_layernorm |
|
- model.layers.6.input_layernorm |
|
- model.layers.7.input_layernorm |
|
- model.layers.8.input_layernorm |
|
- model.layers.9.input_layernorm |
|
- model.layers.10.input_layernorm |
|
- model.layers.11.input_layernorm |
|
- model.layers.12.input_layernorm |
|
- model.layers.13.input_layernorm |
|
- model.layers.14.input_layernorm |
|
- model.layers.15.input_layernorm |
|
- model.layers.16.input_layernorm |
|
- model.layers.17.input_layernorm |
|
- model.layers.18.input_layernorm |
|
- model.layers.19.input_layernorm |
|
- model.layers.20.input_layernorm |
|
- model.layers.21.input_layernorm |
|
- model.layers.22.input_layernorm |
|
- model.layers.23.input_layernorm |
|
- model.layers.24.input_layernorm |
|
- model.layers.25.input_layernorm |
|
- model.layers.26.input_layernorm |
|
- model.layers.27.input_layernorm |
|
- model.layers.28.input_layernorm |
|
- model.layers.29.input_layernorm |
|
- model.layers.30.input_layernorm |
|
- model.layers.31.input_layernorm |
|
# lm_head layers |
|
# mlp.down_proj layers |
|
- model.layers.63.mlp.down_proj |
|
- model.layers.49.mlp.down_proj |
|
- model.layers.48.mlp.down_proj |
|
- model.layers.45.mlp.down_proj |
|
- model.layers.44.mlp.down_proj |
|
- model.layers.47.mlp.down_proj |
|
- model.layers.46.mlp.down_proj |
|
- model.layers.43.mlp.down_proj |
|
- model.layers.8.mlp.down_proj |
|
- model.layers.11.mlp.down_proj |
|
- model.layers.19.mlp.down_proj |
|
- model.layers.35.mlp.down_proj |
|
- model.layers.20.mlp.down_proj |
|
- model.layers.52.mlp.down_proj |
|
- model.layers.39.mlp.down_proj |
|
- model.layers.62.mlp.down_proj |
|
- model.layers.50.mlp.down_proj |
|
- model.layers.29.mlp.down_proj |
|
- model.layers.16.mlp.down_proj |
|
- model.layers.28.mlp.down_proj |
|
- model.layers.53.mlp.down_proj |
|
- model.layers.30.mlp.down_proj |
|
- model.layers.31.mlp.down_proj |
|
- model.layers.32.mlp.down_proj |
|
- model.layers.7.mlp.down_proj |
|
- model.layers.36.mlp.down_proj |
|
- model.layers.12.mlp.down_proj |
|
- model.layers.18.mlp.down_proj |
|
- model.layers.37.mlp.down_proj |
|
- model.layers.38.mlp.down_proj |
|
- model.layers.14.mlp.down_proj |
|
- model.layers.13.mlp.down_proj |
|
# mlp.gate_proj layers |
|
- model.layers.43.mlp.gate_proj |
|
- model.layers.61.mlp.gate_proj |
|
- model.layers.60.mlp.gate_proj |
|
- model.layers.44.mlp.gate_proj |
|
- model.layers.62.mlp.gate_proj |
|
- model.layers.28.mlp.gate_proj |
|
- model.layers.29.mlp.gate_proj |
|
- model.layers.45.mlp.gate_proj |
|
- model.layers.37.mlp.gate_proj |
|
- model.layers.35.mlp.gate_proj |
|
- model.layers.59.mlp.gate_proj |
|
- model.layers.36.mlp.gate_proj |
|
- model.layers.30.mlp.gate_proj |
|
- model.layers.48.mlp.gate_proj |
|
- model.layers.38.mlp.gate_proj |
|
- model.layers.27.mlp.gate_proj |
|
- model.layers.31.mlp.gate_proj |
|
- model.layers.39.mlp.gate_proj |
|
- model.layers.34.mlp.gate_proj |
|
- model.layers.58.mlp.gate_proj |
|
- model.layers.33.mlp.gate_proj |
|
- model.layers.26.mlp.gate_proj |
|
- model.layers.32.mlp.gate_proj |
|
- model.layers.46.mlp.gate_proj |
|
- model.layers.42.mlp.gate_proj |
|
- model.layers.49.mlp.gate_proj |
|
- model.layers.57.mlp.gate_proj |
|
- model.layers.50.mlp.gate_proj |
|
- model.layers.47.mlp.gate_proj |
|
- model.layers.56.mlp.gate_proj |
|
- model.layers.63.mlp.gate_proj |
|
- model.layers.55.mlp.gate_proj |
|
# mlp.up_proj layers |
|
- model.layers.61.mlp.up_proj |
|
- model.layers.60.mlp.up_proj |
|
- model.layers.32.mlp.up_proj |
|
- model.layers.59.mlp.up_proj |
|
- model.layers.58.mlp.up_proj |
|
- model.layers.57.mlp.up_proj |
|
- model.layers.44.mlp.up_proj |
|
- model.layers.28.mlp.up_proj |
|
- model.layers.35.mlp.up_proj |
|
- model.layers.36.mlp.up_proj |
|
- model.layers.31.mlp.up_proj |
|
- model.layers.34.mlp.up_proj |
|
- model.layers.55.mlp.up_proj |
|
- model.layers.29.mlp.up_proj |
|
- model.layers.49.mlp.up_proj |
|
- model.layers.30.mlp.up_proj |
|
- model.layers.53.mlp.up_proj |
|
- model.layers.43.mlp.up_proj |
|
- model.layers.56.mlp.up_proj |
|
- model.layers.33.mlp.up_proj |
|
- model.layers.54.mlp.up_proj |
|
- model.layers.62.mlp.up_proj |
|
- model.layers.27.mlp.up_proj |
|
- model.layers.51.mlp.up_proj |
|
- model.layers.52.mlp.up_proj |
|
- model.layers.37.mlp.up_proj |
|
- model.layers.45.mlp.up_proj |
|
- model.layers.26.mlp.up_proj |
|
- model.layers.42.mlp.up_proj |
|
- model.layers.50.mlp.up_proj |
|
- model.layers.48.mlp.up_proj |
|
- model.layers.39.mlp.up_proj |
|
# model.embed_tokens layers |
|
# model.norm layers |
|
# post_attention_layernorm layers |
|
- model.layers.0.post_attention_layernorm |
|
- model.layers.1.post_attention_layernorm |
|
- model.layers.2.post_attention_layernorm |
|
- model.layers.3.post_attention_layernorm |
|
- model.layers.4.post_attention_layernorm |
|
- model.layers.5.post_attention_layernorm |
|
- model.layers.6.post_attention_layernorm |
|
- model.layers.7.post_attention_layernorm |
|
- model.layers.8.post_attention_layernorm |
|
- model.layers.9.post_attention_layernorm |
|
- model.layers.10.post_attention_layernorm |
|
- model.layers.11.post_attention_layernorm |
|
- model.layers.12.post_attention_layernorm |
|
- model.layers.13.post_attention_layernorm |
|
- model.layers.14.post_attention_layernorm |
|
- model.layers.15.post_attention_layernorm |
|
- model.layers.16.post_attention_layernorm |
|
- model.layers.17.post_attention_layernorm |
|
- model.layers.18.post_attention_layernorm |
|
- model.layers.19.post_attention_layernorm |
|
- model.layers.20.post_attention_layernorm |
|
- model.layers.21.post_attention_layernorm |
|
- model.layers.22.post_attention_layernorm |
|
- model.layers.23.post_attention_layernorm |
|
- model.layers.24.post_attention_layernorm |
|
- model.layers.25.post_attention_layernorm |
|
- model.layers.26.post_attention_layernorm |
|
- model.layers.27.post_attention_layernorm |
|
- model.layers.28.post_attention_layernorm |
|
- model.layers.29.post_attention_layernorm |
|
- model.layers.30.post_attention_layernorm |
|
- model.layers.31.post_attention_layernorm |
|
# self_attn.k_proj layers |
|
- model.layers.63.self_attn.k_proj |
|
- model.layers.55.self_attn.k_proj |
|
- model.layers.60.self_attn.k_proj |
|
- model.layers.7.self_attn.k_proj |
|
- model.layers.12.self_attn.k_proj |
|
- model.layers.13.self_attn.k_proj |
|
- model.layers.57.self_attn.k_proj |
|
- model.layers.29.self_attn.k_proj |
|
- model.layers.14.self_attn.k_proj |
|
- model.layers.51.self_attn.k_proj |
|
- model.layers.53.self_attn.k_proj |
|
- model.layers.54.self_attn.k_proj |
|
- model.layers.22.self_attn.k_proj |
|
- model.layers.61.self_attn.k_proj |
|
- model.layers.18.self_attn.k_proj |
|
- model.layers.30.self_attn.k_proj |
|
- model.layers.9.self_attn.k_proj |
|
- model.layers.24.self_attn.k_proj |
|
- model.layers.23.self_attn.k_proj |
|
- model.layers.25.self_attn.k_proj |
|
- model.layers.10.self_attn.k_proj |
|
- model.layers.58.self_attn.k_proj |
|
- model.layers.56.self_attn.k_proj |
|
- model.layers.15.self_attn.k_proj |
|
- model.layers.32.self_attn.k_proj |
|
- model.layers.28.self_attn.k_proj |
|
- model.layers.8.self_attn.k_proj |
|
- model.layers.59.self_attn.k_proj |
|
- model.layers.11.self_attn.k_proj |
|
- model.layers.48.self_attn.k_proj |
|
- model.layers.16.self_attn.k_proj |
|
- model.layers.50.self_attn.k_proj |
|
# self_attn.o_proj layers |
|
- model.layers.15.self_attn.o_proj |
|
- model.layers.23.self_attn.o_proj |
|
- model.layers.31.self_attn.o_proj |
|
- model.layers.30.self_attn.o_proj |
|
- model.layers.18.self_attn.o_proj |
|
- model.layers.24.self_attn.o_proj |
|
- model.layers.17.self_attn.o_proj |
|
- model.layers.28.self_attn.o_proj |
|
- model.layers.34.self_attn.o_proj |
|
- model.layers.33.self_attn.o_proj |
|
- model.layers.25.self_attn.o_proj |
|
- model.layers.12.self_attn.o_proj |
|
- model.layers.14.self_attn.o_proj |
|
- model.layers.29.self_attn.o_proj |
|
- model.layers.16.self_attn.o_proj |
|
- model.layers.26.self_attn.o_proj |
|
- model.layers.22.self_attn.o_proj |
|
- model.layers.27.self_attn.o_proj |
|
- model.layers.35.self_attn.o_proj |
|
- model.layers.20.self_attn.o_proj |
|
- model.layers.13.self_attn.o_proj |
|
- model.layers.36.self_attn.o_proj |
|
- model.layers.19.self_attn.o_proj |
|
- model.layers.37.self_attn.o_proj |
|
- model.layers.21.self_attn.o_proj |
|
- model.layers.11.self_attn.o_proj |
|
- model.layers.54.self_attn.o_proj |
|
- model.layers.5.self_attn.o_proj |
|
- model.layers.38.self_attn.o_proj |
|
- model.layers.6.self_attn.o_proj |
|
- model.layers.8.self_attn.o_proj |
|
- model.layers.9.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.45.self_attn.q_proj |
|
- model.layers.54.self_attn.q_proj |
|
- model.layers.35.self_attn.q_proj |
|
- model.layers.48.self_attn.q_proj |
|
- model.layers.61.self_attn.q_proj |
|
- model.layers.52.self_attn.q_proj |
|
- model.layers.50.self_attn.q_proj |
|
- model.layers.60.self_attn.q_proj |
|
- model.layers.56.self_attn.q_proj |
|
- model.layers.58.self_attn.q_proj |
|
- model.layers.42.self_attn.q_proj |
|
- model.layers.59.self_attn.q_proj |
|
- model.layers.44.self_attn.q_proj |
|
- model.layers.55.self_attn.q_proj |
|
- model.layers.57.self_attn.q_proj |
|
- model.layers.41.self_attn.q_proj |
|
- model.layers.36.self_attn.q_proj |
|
- model.layers.39.self_attn.q_proj |
|
- model.layers.4.self_attn.q_proj |
|
- model.layers.43.self_attn.q_proj |
|
- model.layers.34.self_attn.q_proj |
|
- model.layers.46.self_attn.q_proj |
|
- model.layers.49.self_attn.q_proj |
|
- model.layers.40.self_attn.q_proj |
|
- model.layers.25.self_attn.q_proj |
|
- model.layers.51.self_attn.q_proj |
|
- model.layers.17.self_attn.q_proj |
|
- model.layers.37.self_attn.q_proj |
|
- model.layers.53.self_attn.q_proj |
|
# self_attn.v_proj layers |
|
- model.layers.55.self_attn.v_proj |
|
- model.layers.31.self_attn.v_proj |
|
- model.layers.47.self_attn.v_proj |
|
- model.layers.45.self_attn.v_proj |
|
- model.layers.49.self_attn.v_proj |
|
- model.layers.48.self_attn.v_proj |
|
- model.layers.15.self_attn.v_proj |
|
- model.layers.30.self_attn.v_proj |
|
- model.layers.7.self_attn.v_proj |
|
- model.layers.44.self_attn.v_proj |
|
- model.layers.29.self_attn.v_proj |
|
- model.layers.51.self_attn.v_proj |
|
- model.layers.50.self_attn.v_proj |
|
- model.layers.14.self_attn.v_proj |
|
- model.layers.54.self_attn.v_proj |
|
- model.layers.32.self_attn.v_proj |
|
- model.layers.43.self_attn.v_proj |
|
- model.layers.10.self_attn.v_proj |
|
- model.layers.46.self_attn.v_proj |
|
- model.layers.38.self_attn.v_proj |
|
- model.layers.57.self_attn.v_proj |
|
- model.layers.22.self_attn.v_proj |
|
- model.layers.39.self_attn.v_proj |
|
- model.layers.6.self_attn.v_proj |
|
- model.layers.23.self_attn.v_proj |
|
- model.layers.58.self_attn.v_proj |
|
- model.layers.53.self_attn.v_proj |
|
- model.layers.40.self_attn.v_proj |
|
- model.layers.24.self_attn.v_proj |
|
- model.layers.9.self_attn.v_proj |
|
- model.layers.25.self_attn.v_proj |
|
- model.layers.5.self_attn.v_proj |
|
|
|
|
|
wandb_project: EVA-Qwen2.5-32B-SFFT-v0.0 |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: Unit-00 |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 1 |
|
num_epochs: 3 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00003 |
|
max_grad_norm: 3 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: true |
|
|
|
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_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: true |
|
# fsdp_offload_params: false # Changed from true |
|
# fsdp_use_orig_params: true # Changed from false |
|
# 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: true # Added |
|
# fsdp_backward_prefetch: "BACKWARD_POST" # Added |
|
# fsdp_backward_prefetch_limit: 1 # Added |
|
# fsdp_mixed_precision: BF16 # Added |
|
``` |
|
|
|
</details><br> |
|
|
