Delta-Vector / Archaeo-32B-KTO

huggingface.co
Total runs: 25
24-hour runs: 0
7-day runs: 4
30-day runs: 11
Model's Last Updated: May 17 2025
text-generation

Introduction of Archaeo-32B-KTO

Model Details of Archaeo-32B-KTO

                        __~a~_
                        ~~;  ~_
          _                ~  ~_                _
         '_\;__._._._._._._]   ~_._._._._._.__;/_`
         '(/'/'/'/'|'|'|'| (    )|'|'|'|'\'\'\'\)'
         (/ / / /, | | | |(/    \) | | | ,\ \ \ \)
        (/ / / / / | | | ~(/    \) ~ | | \ \ \ \ \)
       (/ / / / /  ~ ~ ~   (/  \)    ~ ~  \ \ \ \ \)
      (/ / / / ~          / (||)|          ~ \ \ \ \)
      ~ / / ~            M  /||\M             ~ \ \ ~
       ~ ~                  /||\                 ~ ~
                           //||\\
                           //||\\
                           //||\\
                           '/||\'        "Archaeopteryx"

A series of Merges made for Roleplaying & Creative Writing, This model is a RL train ontop of Archaeo. A merge using Hamanasu-Magnum & Kunou, Trained with Axolotl on 8xH200s.

ChatML formatting
"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
        
Axolotl Configuration
base_model: ./model

plugins:

  • axolotl.integrations.liger.LigerPlugin
  • axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin liger_rope: true liger_rms_norm: true liger_layer_norm: true liger_glu_activation: true liger_fused_linear_cross_entropy: true cut_cross_entropy: false

load_in_8bit: false load_in_4bit: false strict: false

rl: kto kto_undesirable_weight: 1.0

datasets:

  • path: Delta-Vector/Tauri-Opus-Accepted-GPT-Rejected-Opus-Writing-Prompts split: train type: chatml.argilla
  • path: Delta-Vector/Tauri-IFeval-Dans-Tulu-KTO split: train type: chatml.argilla
  • path: Delta-Vector/Tauri-KTO-Instruct-Mix split: train type: chatml.argilla
  • path: Delta-Vector/Tauri-Purpura-Arkhaios-CC-KTO split: train type: chatml.argilla dataset_prepared_path: last_run_prepared val_set_size: 0.0 output_dir: ./archaeo-kto-v2 remove_unused_columns: false

#@lora_mlp_kernel: true #lora_qkv_kernel: true #lora_o_kernel: true

adapter: lora lora_model_dir:

sequence_len: 8192 pad_to_sequence_len: false

lora_r: 64 lora_alpha: 32 lora_dropout: 0.0 lora_target_linear: true lora_fan_in_fan_out: lora_target_modules:

  • gate_proj
  • down_proj
  • up_proj
  • q_proj
  • v_proj
  • k_proj
  • o_proj

wandb_project: Francois-V2 wandb_entity: wandb_watch: wandb_name: Archaeo-32b-KTO wandb_log_model:

gradient_accumulation_steps: 4 micro_batch_size: 4 num_epochs: 1 optimizer: paged_ademamix_8bit lr_scheduler: constant_with_warmup learning_rate: 5e-6 max_grad_norm: 0.001

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

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

warmup_steps: 100 evals_per_epoch: 4 eval_table_size: eval_max_new_tokens: 128 saves_per_epoch: 1 debug: deepspeed: ./deepspeed_configs/zero3_bf16.json weight_decay: 0.0025 fsdp: fsdp_config:

Quants:
Credits

Thank you to: Kubernetes-bad, LucyKnada, Kalomaze, Alicat, Intervitens, Samantha Twinkman, Tav, Trappu & The rest of Anthracite

Runs of Delta-Vector Archaeo-32B-KTO on huggingface.co

25
Total runs
0
24-hour runs
5
3-day runs
4
7-day runs
11
30-day runs

More Information About Archaeo-32B-KTO huggingface.co Model

Archaeo-32B-KTO huggingface.co

Archaeo-32B-KTO huggingface.co is an AI model on huggingface.co that provides Archaeo-32B-KTO's model effect (), which can be used instantly with this Delta-Vector Archaeo-32B-KTO model. huggingface.co supports a free trial of the Archaeo-32B-KTO model, and also provides paid use of the Archaeo-32B-KTO. Support call Archaeo-32B-KTO model through api, including Node.js, Python, http.

Delta-Vector Archaeo-32B-KTO online free

Archaeo-32B-KTO huggingface.co is an online trial and call api platform, which integrates Archaeo-32B-KTO's modeling effects, including api services, and provides a free online trial of Archaeo-32B-KTO, you can try Archaeo-32B-KTO online for free by clicking the link below.

Delta-Vector Archaeo-32B-KTO online free url in huggingface.co:

https://huggingface.co/Delta-Vector/Archaeo-32B-KTO

Archaeo-32B-KTO install

Archaeo-32B-KTO is an open source model from GitHub that offers a free installation service, and any user can find Archaeo-32B-KTO on GitHub to install. At the same time, huggingface.co provides the effect of Archaeo-32B-KTO install, users can directly use Archaeo-32B-KTO installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Archaeo-32B-KTO install url in huggingface.co:

https://huggingface.co/Delta-Vector/Archaeo-32B-KTO

Url of Archaeo-32B-KTO

Provider of Archaeo-32B-KTO huggingface.co

Delta-Vector
ORGANIZATIONS

Other API from Delta-Vector

huggingface.co

Total runs: 32
Run Growth: 8
Growth Rate: 25.00%
Updated:December 31 2024
huggingface.co

Total runs: 32
Run Growth: 9
Growth Rate: 28.13%
Updated:December 31 2024