|
--- |
|
tags: |
|
- chat |
|
- roleplay |
|
- story-writing |
|
datasets: |
|
- NewEden/OpenCAI-ShareGPT |
|
- NewEden/vanilla-backrooms-claude-sharegpt |
|
- anthracite-org/kalo_opus_misc_240827 |
|
- anthracite-org/kalo_misc_part2 |
|
- NewEden/Roleplay-Logs-V2 |
|
Language: |
|
- En |
|
Pipeline_tag: text-generation |
|
Base_model: mistralai/Mistral-Nemo-Instruct-2407 |
|
Tags: |
|
- Chat |
|
base_model: |
|
- mistralai/Mistral-Nemo-Instruct-2407 |
|
--- |
|
|
|
 |
|
|
|
|
|
A finetune of Mistral-Nemo-Instruct-2407 using conversational data, aiming for prose that's best described as 'short' and 'sweet.' The model strictly adheres to one-on-one roleplay and is very dialogue heavy. |
|
|
|
# Quants |
|
|
|
GGUF: https://huggingface.co/Delta-Vector/Ohashi-NeMo-12B-gguf |
|
|
|
EXL2 : https://huggingface.co/Delta-Vector/Ohashi-NeMo-12B-EXL2 |
|
|
|
|
|
## Prompting |
|
Model has been tuned with the Mistral formatting. A typical input would look like this: |
|
|
|
```py |
|
<s>[INST] SYSTEM MESSAGE |
|
USER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST] |
|
|
|
``` |
|
|
|
|
|
## 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> |
|
|
|
Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>. |
|
|
|
``` |
|
</details><br> |
|
|
|
<details><summary>See EVA System Prompt</summary> |
|
|
|
``` |
|
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 -->", |
|
``` |
|
</details><br> |
|
|
|
## Axolotl config |
|
|
|
<details><summary>See axolotl config</summary> |
|
|
|
Axolotl version: ` 0.5.0` |
|
```yaml |
|
base_model: mistralai_Mistral-Nemo-Instruct-2407 |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
datasets: |
|
- path: NewEden/OpenCAI-ShareGPT |
|
type: chat_template |
|
# chat_template: mistralv3tekken |
|
roles_to_train: ["gpt"] |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
train_on_eos: turn |
|
- path: NewEden/vanilla-backrooms-claude-sharegpt |
|
type: chat_template |
|
# chat_template: mistralv3tekken |
|
roles_to_train: ["gpt"] |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
train_on_eos: turn |
|
- path: anthracite-org/kalo_opus_misc_240827 |
|
type: chat_template |
|
# chat_template: mistralv3tekken |
|
roles_to_train: ["gpt"] |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
train_on_eos: turn |
|
- path: anthracite-org/kalo_misc_part2 |
|
type: chat_template |
|
# chat_template: mistralv3tekken |
|
roles_to_train: ["gpt"] |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
train_on_eos: turn |
|
- path: NewEden/Roleplay-Logs-V2 |
|
type: chat_template |
|
# chat_template: mistralv3tekken |
|
roles_to_train: ["gpt"] |
|
field_messages: conversations |
|
message_field_role: from |
|
message_field_content: value |
|
train_on_eos: turn |
|
dataset_prepared_path: dataset_prepared |
|
val_set_size: 0.0 |
|
output_dir: 12b-out-r2 |
|
|
|
sequence_len: 16384 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
adapter: lora |
|
lora_model_dir: |
|
lora_r: 128 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
#lora_target_linear: |
|
#lora_fan_in_fan_out: true |
|
peft_use_rslora: true |
|
lora_target_modules: |
|
- gate_proj |
|
- down_proj |
|
- up_proj |
|
- q_proj |
|
- v_proj |
|
- k_proj |
|
- o_proj |
|
|
|
|
|
wandb_project: 12b-control |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: 12b-control-r2 |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 1 |
|
num_epochs: 4 |
|
optimizer: paged_adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
gradient_checkpointing: unsloth |
|
#gradient_checkpointing_kwargs: |
|
# use_reentrant: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_steps: 40 |
|
evals_per_epoch: |
|
eval_table_size: |
|
eval_max_new_tokens: |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json |
|
weight_decay: 0.03 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
pad_token: <pad> |
|
``` |
|
|
|
</details><br> |
|
|
|
## Credits |
|
|
|
Thank you to [Lucy Knada](https://huggingface.co/lucyknada), [Intervitens](https://huggingface.co/intervitens), [Tav](https://huggingface.co/tavtav), [Trappu](https://huggingface.co/Trappu), [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 4 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 |
|
|
|
 |
