--- license: apache-2.0 language: - en tags: - text-generation base_model: JackFram/llama-68m datasets: - THUDM/webglm-qa - databricks/databricks-dolly-15k - cognitivecomputations/wizard_vicuna_70k_unfiltered - totally-not-an-llm/EverythingLM-data-V3 - Amod/mental_health_counseling_conversations - sablo/oasst2_curated - starfishmedical/webGPT_x_dolly - Open-Orca/OpenOrca - mlabonne/chatml_dpo_pairs widget: - text: |- <|im_start|>system You are a knowledgeable assistant. Help the user as much as you can.<|im_end|> <|im_start|>user How to become healthier?<|im_end|> <|im_start|>assistant - text: |- <|im_start|>system You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.<|im_end|> <|im_start|>user Heya!<|im_end|> <|im_start|>assistant Hi! How may I help you?<|im_end|> <|im_start|>user I am interested in developing a career in software engineering. What would you recommend me to do?<|im_end|> <|im_start|>assistant - text: |- <|im_start|>system You are a helpful assistant who provides concise responses.<|im_end|> <|im_start|>user Hi!<|im_end|> <|im_start|>assistant Hello there! How may I help you?<|im_end|> <|im_start|>user I need to build a simple website. Where should I start learning about web development?<|im_end|> <|im_start|>assistant - text: |- <|im_start|>system You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.<|im_end|> <|im_start|>user Write the background story of an RPG game about wizards and dragons in a sci-fi world.<|im_end|> <|im_start|>assistant inference: parameters: max_new_tokens: 64 penalty_alpha: 0.5 top_k: 4 --- # A Llama Chat Model of 68M Parameters - Base model: [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) - Datasets: - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa) - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) - [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered) - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3) - [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations) - [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated) - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly) - [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) - [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) - Availability in other ML formats: - GGUF: [afrideva/Llama-68M-Chat-v1-GGUF](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF) - ONNX: [Felladrin/onnx-Llama-68M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-68M-Chat-v1) ## Recommended Prompt Format ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {user_message}<|im_end|> <|im_start|>assistant ``` ## Recommended Inference Parameters ```yml penalty_alpha: 0.5 top_k: 4 ```