--- license: apache-2.0 datasets: - trollek/ThoughtfulAssistant-v01 language: - en base_model: h2oai/h2o-danube3-4b-base library_name: transformers --- # ThoughtStream-4B-v0.1 This model is based on [h2oai/h2o-danube3-4b-base](https://huggingface.co/h2oai/h2o-danube3-4b-base) and fine-tuned using [LoRA+](https://arxiv.org/abs/2402.12354 "LoRA+: Efficient Low Rank Adaptation of Large Models") and [BAdam](https://arxiv.org/abs/2404.02827 "BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models") with LLama-Factory. It uses the ChatML template, without a system message, and was trained on the [ThoughtfulAssistant-v01](https://huggingface.co/datasets/trollek/ThoughtfulAssistant-v01) dataset. The idea is to abstract the thoughts away or into a thought bubble when chatting. ### Template ```jinja <|im_start|>user {{instruction}}<|im_end|> <|im_start|>assistant <|thought_start|>{{thinking/rationale}}<|thought_end|> {{response}}<|im_end|> ``` ### Quants One love, [mradermacher](https://huggingface.co/mradermacher). I salute you! - [mradermacher/ThoughtStream-4B-v0.1-GGUF](https://huggingface.co/mradermacher/ThoughtStream-4B-v0.1-GGUF) ### Ollama ```bash ollama run trollek/thoughtstream:4b-v01-q6_K ollama run trollek/thoughtstream:4b-v01-q5_K_S ollama run trollek/thoughtstream:4b-v01-q4_K_S ``` ### Response preview #### USER >Do you know of any books that could be called a cross between Discworld and The Three Body Problem? #### ASSISTANT > <|thought_start|>The user is asking for recommendations that combine elements from both Discworld by Terry Pratchett and The Three Body Problem by Liu Cixin. This means they're looking for stories with a similar sense of humor, fantastical settings, and complex political structures as Discworld, but also with the scientific themes and intricate plotting found in The Three Body Problem. I need to find books that meet these criteria without being too repetitive or predictable. Hmm... let me think about some options. > > One possibility could be "The City We Became" by N.K. Jemisin, which has a similar blend of urban fantasy and science fiction elements with its depiction of New York as an alive city. Another option might be "The Martian Chronicles" by Ray Bradbury, another classic work that combines science fiction, humor, and social commentary in the context of humanity's exploration of Mars. But I should also consider some more recent works like "Solaris" by Stanislaw Lem or "The City of Thieves" by David Benioff, which have similar themes to The Three Body Problem but are less well-known. > > Ultimately, I think the best choice would be "The City We Became," as it combines elements from both Discworld and The Three Body Problem in a unique way while also being a great read on its own merits.<|thought_end|> > >I'm sorry, but there isn't an exact book that fits your description of a cross between Discworld and The Three Body Problem. However, "The City We Became" by N.K. Jemisin is often compared to both series due to its blend of urban fantasy with elements of science fiction and social commentary. It also has a similar sense of humor as Discworld while incorporating some of the intricate plotting found in The Three Body Problem. ### LLama-Factory configs ```yaml ### model model_name_or_path: danube3/thinking-base-chatml ### method stage: sft do_train: true finetuning_type: lora lora_target: all loraplus_lr_ratio: 16.0 quantization_bit: 4 lora_rank: 8 lora_alpha: 16 use_unsloth: true upcast_layernorm: true seed: 24 additional_target: embed_tokens ### dataset dataset: thinking_phi3,thinking_capybara,thinking_qwen2,thinking_panoia template: hermes_chatml cutoff_len: 8192 overwrite_cache: false preprocessing_num_workers: 12 ### output output_dir: danube3/thinking-base-chatml/thoughtful_loraplus logging_steps: 1 save_steps: 1 save_strategy: epoch plot_loss: true overwrite_output_dir: false ### train per_device_train_batch_size: 4 gradient_accumulation_steps: 4 learning_rate: 0.00001 num_train_epochs: 2 lr_scheduler_type: cosine warmup_ratio: 0.01 bf16: true flash_attn: fa2 ### eval val_size: 0.01 per_device_eval_batch_size: 1 eval_strategy: steps eval_steps: 500 ``` ```yaml ### model model_name_or_path: danube3/thinking-base-chatml/merged_loraplus ### method stage: sft do_train: true finetuning_type: full use_badam: true badam_switch_mode: ascending badam_start_block: 7 badam_switch_interval: 20 badam_verbose: 1 seed: 768 ### dataset dataset: thinking_capybara,thinking_panoia template: hermes_chatml cutoff_len: 8192 overwrite_cache: false preprocessing_num_workers: 12 ### output output_dir: danube3/ThoughtStream-4B-v0.1 logging_steps: 1 save_steps: 1 save_strategy: epoch plot_loss: true overwrite_output_dir: false ### train per_device_train_batch_size: 1 gradient_accumulation_steps: 4 learning_rate: 0.00001 num_train_epochs: 1 lr_scheduler_type: constant_with_warmup warmup_ratio: 0.01 pure_bf16: true flash_attn: fa2 ### eval val_size: 0.01 per_device_eval_batch_size: 1 eval_strategy: steps eval_steps: 200 ```