Views
No views yet

1"""<|im_start|>user
2Hi there!<|im_end|>
3<|im_start|>assistant
4Nice to meet you!<|im_end|>
5<|im_start|>user
6Can I ask a question?<|im_end|>
7<|im_start|>assistant
8"""
9Currently, 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>.
0.5.01base_model: Delta-Vector_Francois-PE-12B
2
3load_in_8bit: false
4load_in_4bit: false
5strict: false
6
7rl: kto
8kto_undesirable_weight: 1.0
9
10#datasets:
11# - ds_type: json
12# data_files:
13# - NewEden/Ohashi-accepted-Hermes-rejected
14# split: train
15# type: chatml.argilla
16datasets:
17 - path: NewEden/Opus-accepted-hermes-rejected-shuffled
18 split: train
19 type: chatml.argilla
20dataset_prepared_path: last_run_prepared
21val_set_size: 0.0
22output_dir: ./francois-PE-kto-r1
23
24remove_unused_columns: false
25
26adapter: lora
27lora_model_dir:
28
29sequence_len: 8192
30pad_to_sequence_len: false
31
32lora_r: 64
33lora_alpha: 32
34lora_dropout: 0.0
35lora_target_linear: true
36lora_fan_in_fan_out:
37lora_target_modules:
38 - gate_proj
39 - down_proj
40 - up_proj
41 - q_proj
42 - v_proj
43 - k_proj
44 - o_proj
45
46wandb_project: KTO-NeMo
47wandb_entity:
48wandb_watch:
49wandb_name: Ohashi-accepted-hermes-rejected-r1
50wandb_log_model:
51
52gradient_accumulation_steps: 4
53micro_batch_size: 2
54num_epochs: 1
55optimizer: paged_adamw_8bit
56lr_scheduler: constant_with_warmup
57learning_rate: 1e-6
58max_grad_norm: 0.01
59
60train_on_inputs: false
61group_by_length: false
62bf16: auto
63fp16:
64tf32: true
65
66gradient_checkpointing: unsloth
67early_stopping_patience:
68resume_from_checkpoint:
69local_rank:
70logging_steps: 1
71xformers_attention:
72flash_attention: true
73
74warmup_steps: 25
75evals_per_epoch: 4
76eval_table_size:
77eval_max_new_tokens: 128
78saves_per_epoch: 1
79debug:
80deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
81weight_decay: 0.0
82fsdp:
83fsdp_config:
84
85