---
tags:
- chat
datasets:
- NewEden/OpenCAI-ShareGPT
- NewEden/vanilla-backrooms-claude-sharegpt
- anthracite-org/kalo_opus_misc_240827
- anthracite-org/kalo_misc_part2
- NewEden/RP-logs-V2-Experimental
- NewEden/BlueSky-Experimental-sharegpt
- NewEden/Misc-Mang-Sharegpt
- NewEden/Opus-accepted-hermes-rejected-shuffled
Language:
- En
Pipeline_tag: text-generation
Base_model: Delta-Vector/Francois-PE-12B
Tags:
- Chat
---
### exl2 quant (measurement.json in main branch)
---
### check revisions for quants
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/EXbNn0z9o5TCc2RF6An66.png)


A finetune ontop of the original Francois-PE model that incorporates KTO to increase coherency and prose. The model aims to have short and sweet prose.


# Quants 

GGUF: https://huggingface.co/Delta-Vector/Francois-Huali-12B-gguf

EXL2 : https://huggingface.co/Delta-Vector/Francois-Huali-12B-exl2


## Prompting
Model has been tuned with the ChatML formatting. A typical input would look like this:

```py
"""<|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
"""

```


## System Prompting

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

<details><summary>See Sao10k's Euryale System Prompt</summary>

```
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>Thanks to Po

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

```
</details><br>

### exl2 quant (measurement.json in main branch)
---
### check revisions for quants
---

## Axolotl config

<details><summary>See axolotl config</summary>

Axolotl version: ` 0.5.0`
```yaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

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: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

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

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

warmup_steps: 25
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
weight_decay: 0.0
fsdp:
fsdp_config:


```

</details><br>

## Credits

Thank you to [Lucy Knada](https://huggingface.co/lucyknada), [Intervitens](https://huggingface.co/intervitens),[Cgato](https://huggingface.co/cgato), [Kubernetes Bad](https://huggingface.co/kubernetes-bad) and the rest of [Anthracite](https://huggingface.co/anthracite-org) 


## Training
The training was done for 1 epochs We used  4 x [RTX 3090s](https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/rtx-3090-3090ti/) GPUs graciously provided by [Intervitens](https://huggingface.co/intervitens) for the fine-tuning of the model. 

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

## Safety

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/bL0o_4bvbkmzAvK3W8gu2.png)