Views
No views yet
| Type | Link |
|---|---|
GGUF | Waiting for Mradermacher to quant |
EXL2 | https://huggingface.co/Delta-Vector/Hamanasu-Magnum-QwQ-32B-exl2 |
Delta-Vector/Hamanasu-QwQ-V2-RP1<|im_start|>system
2You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
3<|im_start|>User request
4Take off your helmet.<|im_end|>
5<|im_start|>No i shall not. This is the way.1temperature: 1.1
2min_p: 0.1
3System_Prompt: Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.\n\n<Guidelines>\n• Maintain the character persona but allow it to evolve with the story.\n• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.\n• All types of outputs are encouraged; respond accordingly to the narrative.\n• Include dialogues, actions, and thoughts in each response.\n• Utilize all five senses to describe scenarios within {{char}}'s dialogue.\n• Use emotional symbols such as \"!\" and \"~\" in appropriate contexts.\n• Incorporate onomatopoeia when suitable.\n• Allow time for {{user}} to respond with their own input, respecting their agency.\n• Act as secondary characters and NPCs as needed, and remove them when appropriate.\n• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.\n</Guidelines>\n\n<Forbidden>\n• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.\n• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.\n• Repetitive and monotonous outputs.\n• Positivity bias in your replies.\n• Being overly extreme or NSFW when the narrative context is inappropriate.\n</Forbidden>\n\nFollow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.1base_model: ./model
2model_type: AutoModelForCausalLM
3tokenizer_type: AutoTokenizer
4
5hub_model_id: NewEden/QwQ-magnum-V2-R2
6hub_strategy: "all_checkpoints"
7push_dataset_to_hub:
8hf_use_auth_token: true
9
10plugins:
11 - axolotl.integrations.liger.LigerPlugin
12 - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
13liger_rope: true
14liger_rms_norm: true
15liger_layer_norm: true
16liger_glu_activation: true
17liger_fused_linear_cross_entropy: false
18cut_cross_entropy: true
19
20load_in_8bit: false
21load_in_4bit: false
22strict: false
23
24datasets:
25 - path: PocketDoc/Dans-Personamaxx-Logs
26 type: dan-chat-advanced
27 - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
28 type: dan-chat-advanced
29 - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
30 type: dan-chat-advanced
31 - path: anthracite-org/nopm_claude_writing_fixed
32 type: dan-chat-advanced
33 - path: anthracite-org/kalo_opus_misc_240827
34 type: dan-chat-advanced
35 - path: anthracite-org/kalo_misc_part2
36 type: dan-chat-advanced
37 - path: NewEden/Claude-Instruct-5K
38 type: dan-chat-advanced
39 - path: NewEden/Claude-Instruct-2.7K
40 type: dan-chat-advanced
41dataset_prepared_path: prepared_data
42val_set_size: 0.0
43output_dir: ./qwq-mag
44sequence_len: 32768
45sample_packing: true
46pad_to_sequence_len: true
47
48wandb_project: qwq
49wandb_entity:
50wandb_watch:
51wandb_name: mag-attempt-03-kalo
52wandb_log_model:
53
54
55gradient_accumulation_steps: 2
56micro_batch_size: 2
57num_epochs: 2
58optimizer: paged_adamw_8bit
59lr_scheduler: cosine
60learning_rate: 5e-6
61max_grad_norm: 0.2
62
63train_on_inputs: false
64group_by_length: false
65bf16: auto
66fp16:
67tf32: false
68
69
70gradient_checkpointing: unsloth
71early_stopping_patience:
72resume_from_checkpoint:
73local_rank:
74logging_steps: 1
75xformers_attention:
76flash_attention: true
77
78warmup_steps: 40
79saves_per_epoch: 2
80debug:
81deepspeed: ./deepspeed_configs/zero3_bf16.json
82weight_decay: 0.02
83fsdp:
84fsdp_config:
85special_tokens:
