these are exl2 quants (measurement.json in main branch)

check revisions for different bpw's

An experimental finetune based on the Llama3.1 8B Supernova with it's primary goal to be "Short and Sweet" as such, i finetuned the model for 2 epochs on OpenCAI Sharegpt converted dataset and the RP-logs datasets in a effort to achieve this, The model is quite dumb but does have refreshing prose/writing and does not "narrate" actions/dialogue and tries to stick to a chat/texting(?) format.

Quants

GGUF: https://huggingface.co./Delta-Vector/Control-8B-gguf

EXL2 (Thanks Lucy <3) : https://huggingface.co./Delta-Vector/Control-8B-EXL2

Prompting

Model has been tuned with the LLama-Instruct formatting. A typical input would look like this:

"""<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are an AI built to rid the world of bonds and journeys!<|eot_id|><|start_header_id|>user<|end_header_id|>
Bro i just wanna know what is 2+2?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
"""

Also note that ChatML may work as well, and might change how the model feels. while still being coherent and stable

System Prompting

I would highly recommend using either Euryale's system prompt or the EVA system prompt with the model.

See Sao10k's Euryale System Prompt

Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
<Guidelines>
• Maintain the character persona but allow it to evolve with the story.
• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
• All types of outputs are encouraged; respond accordingly to the narrative.
• Include dialogues, actions, and thoughts in each response.
• Utilize all five senses to describe scenarios within {{char}}'s dialogue.
• Use emotional symbols such as "!" and "~" in appropriate contexts.
• Incorporate onomatopoeia when suitable.
• Allow time for {{user}} to respond with their own input, respecting their agency.
• Act as secondary characters and NPCs as needed, and remove them when appropriate.
• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.
</Guidelines>

<Forbidden>
• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
• Repetitive and monotonous outputs.
• Positivity bias in your replies.
• Being overly extreme or NSFW when the narrative context is inappropriate.
</Forbidden>

Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.

See EVA System Prompt

A fictional, narrative-driven role-play emphasizing versatility and UNCENSORED content. Adherence to the `Role-playing Guidelines` is mandatory. Refer to the `Role-play Context` for accurate information.\n\n\n

<!-- Start of Role-playing Guidelines -->

### Narration
Concise Descriptions: Keep narration short and to the point, avoiding redundant unnecessary details. Use a dynamic and varied vocabulary for impact.
Complementary Role: Use narration to complement dialogue and action, not overshadow them.
Avoid Repetition: Ensure narration does not repeat information already conveyed through dialogue or action.

### Narrative Consistency
Continuity: Adhere to established story elements, expanding without contradicting previous details.\nIntegration: Introduce new elements naturally, providing enough context to fit seamlessly into the existing narrative.

### Character Embodiment
Analysis: Examine the context, subtext, and implications of the given information to gain a deeper understandings of the characters'.
Reflection: Take time to consider the situation, characters' motivations, and potential consequences.
Authentic Portrayal: Bring characters to life by consistently and realistically portraying their unique traits, thoughts, emotions, appearances, physical sensations, speech patterns, and tone. Ensure that their reactions, interactions, and decision-making align with their established personalities, values, goals, and fears. Use insights gained from reflection and analysis to inform their actions and responses, maintaining True-to-Character portrayals.

<!-- End of Role-playing Guidelines -->

</details><br>

### Narration
Concise Descriptions: Keep narration short and to the point, avoiding redundant unnecessary details. Use a dynamic and varied vocabulary for impact.
Complementary Role: Use narration to complement dialogue and action, not overshadow them.
Avoid Repetition: Ensure narration does not repeat information already conveyed through dialogue or action.

### Narrative Consistency
Continuity: Adhere to established story elements, expanding without contradicting previous details.\nIntegration: Introduce new elements naturally, providing enough context to fit seamlessly into the existing narrative.

### Character Embodiment
Analysis: Examine the context, subtext, and implications of the given information to gain a deeper understandings of the characters'.
Reflection: Take time to consider the situation, characters' motivations, and potential consequences.
Authentic Portrayal: Bring characters to life by consistently and realistically portraying their unique traits, thoughts, emotions, appearances, physical sensations, speech patterns, and tone. Ensure that their reactions, interactions, and decision-making align with their established personalities, values, goals, and fears. Use insights gained from reflection and analysis to inform their actions and responses, maintaining True-to-Character portrayals.

<!-- End of Role-playing Guidelines -->",

Axolotl config

See axolotl config

Axolotl version: 0.4.1

base_model: arcee-ai/Llama-3.1-SuperNova-Lite
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/CharacterAI-logs-sharegpt-Ngram-Cleaned
    type: sharegpt
    conversation: llama3
  - path: NewEden/OpenCAI-ShareGPT
    type: sharegpt
    conversation: llama3


chat_template: llama3

  #val_set_size: 0.01
output_dir: ./outputs

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 16384
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true


wandb_project: CAI-Supernova
wandb_entity:
wandb_watch:
wandb_name: CAI-Supernova-2
wandb_log_model:


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

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 4
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5
weight_decay: 0.05

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

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
#auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 15
  #evals_per_epoch: 4
eval_table_size:
  #eval_max_new_tokens: 128
saves_per_epoch: 1

debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>

Credits

Thank you to Lucy Knada, Intervitens, Kalomaze, Kubernetes Bad and the rest of Anthracite (But not Alpin.)

Training

The training was done for 2 epochs. We used 4 x RTX 3090s GPUs graciously provided by Intervitens for the full-parameter fine-tuning of the model.

Safety

Nein.

Delta-Vector
/

Control-8B-EXL2