--- license: apache-2.0 language: - en tags: - chat pipeline_tag: text-generation library_name: transformers --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/ZmOOkB2QwItLmoqmnxNWO.png) This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. experimental because trained on top of instruct; but turned out amazing; hence code named magnum-alter, the original model that kickstarted the v4 family This model is fine-tuned on top of [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct). ## Prompting A typical input would look like this: ```py <|im_start|>system system prompt<|im_end|> <|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 ``` ## SillyTavern templates Below are Instruct and Context templates for use within SillyTavern.
context template ```yaml { "story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n", "example_separator": "", "chat_start": "", "use_stop_strings": false, "allow_jailbreak": false, "always_force_name2": true, "trim_sentences": false, "include_newline": false, "single_line": false, "name": "Magnum ChatML" } ```

instruct template ```yaml { "system_prompt": "Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.\n\n\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\n\n\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\n\nFollow the instructions in , avoiding the items listed in .", "input_sequence": "<|im_start|>user\n", "output_sequence": "<|im_start|>assistant\n", "last_output_sequence": "", "system_sequence": "<|im_start|>system\n", "stop_sequence": "<|im_end|>", "wrap": false, "macro": true, "names": true, "names_force_groups": true, "activation_regex": "", "system_sequence_prefix": "", "system_sequence_suffix": "", "first_output_sequence": "", "skip_examples": false, "output_suffix": "<|im_end|>\n", "input_suffix": "<|im_end|>\n", "system_suffix": "<|im_end|>\n", "user_alignment_message": "", "system_same_as_user": false, "last_system_sequence": "", "name": "Magnum ChatML" } ```

## Axolotl config
See axolotl config ```yaml base_model: /workspace/data/models/Qwen2.5-72B-Instruct 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: anthracite-org/c2_logs_32k_llama3_qwen2_v1.2 type: sharegpt conversation: chatml - path: anthracite-org/kalo-opus-instruct-22k-no-refusal type: sharegpt conversation: chatml - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered type: sharegpt conversation: chatml - path: anthracite-org/nopm_claude_writing_fixed type: sharegpt conversation: chatml - path: anthracite-org/kalo_opus_misc_240827 type: sharegpt conversation: chatml - path: anthracite-org/kalo_misc_part2 type: sharegpt conversation: chatml #chat_template: chatml shuffle_merged_datasets: true #default_system_message: "You are an assistant that responds to the user." dataset_prepared_path: /workspace/data/magnum-72b-data val_set_size: 0.0 output_dir: /workspace/data/72b-fft-out sequence_len: 32768 sample_packing: true pad_to_sequence_len: true adapter: lora_model_dir: lora_r: lora_alpha: lora_dropout: lora_target_linear: lora_fan_in_fan_out: wandb_project: 72b-magnum-fft wandb_entity: wandb_watch: wandb_name: alter-attempt-01 wandb_log_model: gradient_accumulation_steps: 2 micro_batch_size: 1 num_epochs: 2 optimizer: adamw_bnb_8bit lr_scheduler: cosine learning_rate: 0.000004 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true 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: 2 debug: deepspeed: deepspeed_configs/zero3_bf16.json weight_decay: 0.01 fsdp: fsdp_config: special_tokens: ```

## Credits We'd like to thank [DoctorShotgun](https://huggingface.co/Doctor-Shotgun) for sponsoring the compute for this train. We would also like to thank all members of Anthracite who made this finetune possible. ## Datasets - [anthracite-org/c2_logs_32k_llama3_qwen2_v1.2](https://huggingface.co/datasets/anthracite-org/c2_logs_32k_llama3_qwen2_v1.2) - [anthracite-org/kalo-opus-instruct-22k-no-refusal](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal) - [lodrick-the-lafted/kalo-opus-instruct-3k-filtered](https://huggingface.co/datasets/lodrick-the-lafted/kalo-opus-instruct-3k-filtered) - [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed) - [anthracite-org/kalo_opus_misc_240827](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827) - [anthracite-org/kalo_misc_part2](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2) ## Training We used 8x mi300x GPUs graciously provided by [DoctorShotgun](https://huggingface.co/Doctor-Shotgun) for the full-parameter fine-tuning of the model. [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) ## Safety ...