Delta-Vector / Hamanasu-4B-Chat-Brainrot

huggingface.co
Total runs: 17
24-hour runs: 0
7-day runs: -1
30-day runs: 25
Model's Last Updated: April 07 2025

Introduction of Hamanasu-4B-Chat-Brainrot

Model Details of Hamanasu-4B-Chat-Brainrot

Model Visualization

Hamanasu 4B
🌌 Overview

This model is the Chat tune of the Instruct model, More accurately it is the "brainrotted" version, Finetuned with Bsky, 4chan and Discord logs, Its... really something beautiful.

The model is suited best towards being a highly dumb chat partner rather then regular RP

The model is suited for traditional RP, All thanks to Tav for funding the train.

Support me and my finetunes on Ko-Fi https://ko-fi.com/deltavector

⚔️ Hardware
  • 8x H100s
  • Epochs: 4
  • Base: Delta-Vector/Hamanasu-4B-Instruct-KTO-V2
💰 Prompting

This model uses ChatML formatting

<|im_start|>system
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
<|im_start|>User request
Take off your helmet.<|im_end|>
<|im_start|>No i shall not. This is the way.
🎲 Recommended Sampler Preset
ST sampler preset: https://files.catbox.moe/wtkp0l.json
System prompt: Blank.
Axolotl Config ꒰(˶• ᴗ •˶)꒱
ase_model: ./model                                                                                                                                            
model_type: AutoModelForCausalLM                  
tokenizer_type: AutoTokenizer                     
                                                                                                                                                               
hub_model_id: NewEden/Hamanasu-4B-RP-v2   
hub_strategy: "all_checkpoints"       
push_dataset_to_hub:                                                     
hf_use_auth_token: true                  
## qlora COPE                            
load_in_8bit: false                                                            
load_in_4bit: false                                                            
strict: false                                                          
                                                                               
## data                                   
datasets:                                                                                                                                                      
  - path: NewEden/Discord-Filtered                                             
    type: dan-chat-advanced                                                                                                                                                                                                                                                                                                    
  - path: NewEden/Basket-Weaving-Filtered         
    type: dan-chat-advanced               
  - path: NewEden/Misc-Data-Sharegpt-Prefixed                                  
    type: dan-chat-advanced     
  - path: NewEden/BlueSky-10K-Complexity 
    type: dan-chat-advanced                                                    
  - path: PocketDoc/Dans-Kinomaxx-VanillaBackrooms
    type: dan-chat-advanced                                                    
  - path: PocketDoc/Dans-Personamaxx-VN                                        
    type: dan-chat-advanced 
  - path: NewEden/LIMARP-Complexity       
    type: dan-chat-advanced
  - path: NewEden/OpenCAI-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Creative_Writing-Complexity                                  
    type: dan-chat-advanced           
  - path: NewEden/DeepseekRP-Filtered                                          
    type: dan-chat-advanced       
  - path: NewEden/Storium-Prefixed-Clean                                       
    type: dan-chat-advanced              
shuffle_merged_datasets: true
dataset_prepared_path: dataset_prepared-2    
val_set_size: 0.01                                                             
output_dir: 4b-out                      
                                                                               
## LIGGER                                                                      
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: false
cut_cross_entropy: true
                                                                               
## CTX settings            
sequence_len: 32768                                                            
sample_packing: true       
eval_sample_packing: false                
pad_to_sequence_len: true  
                                                                               
## Lora                                                                        
#adapter: lora    
#lora_model_dir:                                                               
#lora_r: 128                                                                   
#lora_alpha: 16                                                                
#lora_dropout: 0.05                   
#lora_target_modules:                     
#  - gate_proj                                                                                 
#  - down_proj                                                                                 
#  - up_proj                                                                                   
#  - q_proj                                                                                    
#  - v_proj                                                                                    
#  - k_proj                                                                                    
#  - o_proj                                                                                                            
#lora_fan_in_fan_out:                                                                          
#peft_use_rslora: true                                                                         
#lora_modules_to_save:                                                                         
#  - embed_tokens                                                                              
#  - lm_head                                                                                   
                                                                                               
## WandB                                                                                       
wandb_project: tavbussy                                                                        
wandb_entity:                                                                                  
wandb_watch:                                                                                   
wandb_name: chat-v2                                                                                                    
wandb_log_model:                                                                                                       
                                                                                                                       
## evals                                                                                                               
evals_per_epoch: 4                                                                                                     
eval_table_size:                                                                                                       
eval_max_new_tokens: 128                                                                                               
                                                                                                                       
## hoe params                                                                                                          
gradient_accumulation_steps: 2                                                                                         
micro_batch_size: 1                                                                                                    
num_epochs: 4                                                                                                          
optimizer: adamw_bnb_8bit                                                                                              
lr_scheduler: cosine                                                                                                                                           
learning_rate: 2e-5                                                                                                    
max_grad_norm: 0.2                                                                                                     
train_on_inputs: false                                                                                                 
group_by_length: false                                                                                                 
bf16: auto                                                                                                             
fp16:                                                                                                                  
tf32: false                                                                                                            
                                                                                                                       
gradient_checkpointing: true                                                                                           
early_stopping_patience:                                                                                               
resume_from_checkpoint:                                                                                                                                        
local_rank:                                                                                                                                                    
logging_steps: 1                                                                                                                                               
xformers_attention:                                                                                                                                            
flash_attention: true                                                                                                                                          
s2_attention:                                                                                                                                                  

warmup_steps: 40                                                                                                                                               
saves_per_epoch: 2                                                                                                                                             
debug:                                                                                                                                                         
deepspeed: ./deepspeed_configs/zero3_bf16.json                                                                                                                 
weight_decay: 0.02                                                                                                                                             
fsdp:                                                                                                                                                          
fsdp_config:                                                                                                                                            
special_tokens:                                                                                                                        
  pad_token: <|finetune_right_pad_id|>       
⚡ Credits

Made by
Delta-Vector

Runs of Delta-Vector Hamanasu-4B-Chat-Brainrot on huggingface.co

17
Total runs
0
24-hour runs
-2
3-day runs
-1
7-day runs
25
30-day runs

More Information About Hamanasu-4B-Chat-Brainrot huggingface.co Model

Hamanasu-4B-Chat-Brainrot huggingface.co

Hamanasu-4B-Chat-Brainrot huggingface.co is an AI model on huggingface.co that provides Hamanasu-4B-Chat-Brainrot's model effect (), which can be used instantly with this Delta-Vector Hamanasu-4B-Chat-Brainrot model. huggingface.co supports a free trial of the Hamanasu-4B-Chat-Brainrot model, and also provides paid use of the Hamanasu-4B-Chat-Brainrot. Support call Hamanasu-4B-Chat-Brainrot model through api, including Node.js, Python, http.

Hamanasu-4B-Chat-Brainrot huggingface.co Url

https://huggingface.co/Delta-Vector/Hamanasu-4B-Chat-Brainrot

Delta-Vector Hamanasu-4B-Chat-Brainrot online free

Hamanasu-4B-Chat-Brainrot huggingface.co is an online trial and call api platform, which integrates Hamanasu-4B-Chat-Brainrot's modeling effects, including api services, and provides a free online trial of Hamanasu-4B-Chat-Brainrot, you can try Hamanasu-4B-Chat-Brainrot online for free by clicking the link below.

Delta-Vector Hamanasu-4B-Chat-Brainrot online free url in huggingface.co:

https://huggingface.co/Delta-Vector/Hamanasu-4B-Chat-Brainrot

Hamanasu-4B-Chat-Brainrot install

Hamanasu-4B-Chat-Brainrot is an open source model from GitHub that offers a free installation service, and any user can find Hamanasu-4B-Chat-Brainrot on GitHub to install. At the same time, huggingface.co provides the effect of Hamanasu-4B-Chat-Brainrot install, users can directly use Hamanasu-4B-Chat-Brainrot installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Hamanasu-4B-Chat-Brainrot install url in huggingface.co:

https://huggingface.co/Delta-Vector/Hamanasu-4B-Chat-Brainrot

Url of Hamanasu-4B-Chat-Brainrot

Hamanasu-4B-Chat-Brainrot huggingface.co Url

Provider of Hamanasu-4B-Chat-Brainrot huggingface.co

Delta-Vector
ORGANIZATIONS

Other API from Delta-Vector

huggingface.co

Total runs: 30
Run Growth: 12
Growth Rate: 40.00%
Updated:December 31 2024
huggingface.co

Total runs: 25
Run Growth: 5
Growth Rate: 20.00%
Updated:December 31 2024