--- language: - en license: agpl-3.0 tags: - chat base_model: - nvidia/Mistral-NeMo-Minitron-8B-Base datasets: - anthracite-org/c2_logs_16k_llama_v1.1 - anthracite-org/kalo-opus-instruct-22k-no-refusal - Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned - lodrick-the-lafted/kalo-opus-instruct-3k-filtered - anthracite-org/nopm_claude_writing_fixed - Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned - anthracite-org/kalo_opus_misc_240827 - anthracite-org/kalo_misc_part2 License: agpl-3.0 Language: - En Pipeline_tag: text-generation Base_model: nvidia/Mistral-NeMo-Minitron-8B-Base Tags: - Chat model-index: - name: Darkens-8B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 25.48 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 32.88 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 5.06 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 9.96 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 9.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 30.4 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Delta-Vector/Darkens-8B name: Open LLM Leaderboard --- This is the fully cooked, 4 epoch version of [Tor-8B](https://huggingface.co/Delta-Vector/Tor-8B), this is an experimental version, despite being trained for 4 epochs, the model feels fresh and new and is not overfit, This model aims to have generally good prose and writing while not falling into claude-isms, it follows the *actions* "dialogue" format heavily. # Quants GGUF: https://huggingface.co/Delta-Vector/Darkens-8B-GGUF EXL2: https://huggingface.co/Delta-Vector/Darkens-8B-EXL2 ## Prompting Model has been Instruct tuned with the ChatML formatting. 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 """ ``` ## System Prompting I would highly recommend using Sao10k's Euryale System prompt, But the "Roleplay Simple" system prompt provided within SillyTavern will work aswell. ``` Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}. • 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}}. • 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. Follow the instructions in , avoiding the items listed in . ``` ## Axolotl config
See axolotl config Axolotl version: `0.4.1` ```yaml base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer plugins: - axolotl.integrations.liger.LigerPlugin liger_rope: true liger_rms_norm: true liger_swiglu: true #liger_cross_entropy: true liger_fused_linear_cross_entropy: true load_in_8bit: false load_in_4bit: false strict: false datasets: - path: anthracite-org/c2_logs_16k_llama_v1.1 type: sharegpt conversation: chatml - path: anthracite-org/kalo-opus-instruct-22k-no-refusal type: sharegpt conversation: chatml - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned 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: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned 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: false default_system_message: "You are a helpful assistant that responds to the user." dataset_prepared_path: /workspace/data/8b-nemo-fft-data val_set_size: 0.0 output_dir: /workspace/data/8b-nemo-fft-out sequence_len: 16384 sample_packing: true eval_sample_packing: false 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: 8b-nemoprune-fft wandb_entity: wandb_watch: wandb_name: attempt-01 wandb_log_model: gradient_accumulation_steps: 2 micro_batch_size: 2 num_epochs: 4 optimizer: adamw_bnb_8bit lr_scheduler: cosine learning_rate: 0.00001 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: /workspace/workspace/thing local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: eval_table_size: eval_max_new_tokens: saves_per_epoch: 1 debug: deepspeed: deepspeed_configs/zero3_bf16.json weight_decay: 0.001 fsdp: fsdp_config: special_tokens: pad_token: ```

## Credits Thank you to [Lucy Knada](https://huggingface.co/lucyknada), [Kalomaze](https://huggingface.co/kalomaze), [Kubernetes Bad](https://huggingface.co/kubernetes-bad) and the rest of [Anthracite](https://huggingface.co/anthracite-org) (But not Alpin.) ## Training The training was done for 4 epochs. I used 10 x [A40s](https://www.nvidia.com/en-us/data-center/a40/) GPUs graciously provided by [Kalomaze](https://huggingface.co/kalomaze) for the full-parameter fine-tuning of the model. [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Delta-Vector__Darkens-8B) | Metric |Value| |-------------------|----:| |Avg. |18.80| |IFEval (0-Shot) |25.48| |BBH (3-Shot) |32.88| |MATH Lvl 5 (4-Shot)| 5.06| |GPQA (0-shot) | 9.96| |MuSR (0-shot) | 9.02| |MMLU-PRO (5-shot) |30.40|