dphn

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations This is our most spectacular outcome ever. FFT, all parameters, 16bit. 77.4 MMLU on 34b. And it talks like a dream. Although the max positional embeddings is 4k, we used rope theta of 1000000.0 and we trained with sequence length 8k. We plan to train on the upcoming 32k version as well. Website: https://dphn.ai Twitter: https://x.com/dphnAI Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot Our appreciation for the sponsors of Dolphin 2.9.1: - Crusoe Cloud - provided excellent on-demand 8xH100 node - OnDemand - provided inference sponsorship This model is based on Yi-1.5-34b, and is governed by apache 2.0 license. The base model has 4k context, but we used rope theta of 1000000.0 and the full-weight fine-tuning was with 8k sequence length. Dolphin-2.9.1 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly. Dolphin is licensed according to apache 2.0 license. We grant permission for any use, including commercial. Dolphin was trained on data generated from GPT4, among other models. This model is a fine-tuned version of 01-ai/Yi-1.5-34B on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4425 The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 1 - evalbatchsize: 1 - seed: 42 - distributedtype: multi-GPU - numdevices: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - totalevalbatchsize: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: cosine - lrschedulerwarmupsteps: 10 - numepochs: 3 | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.6265 | 0.0 | 1 | 0.6035 | | 0.4674 | 0.25 | 327 | 0.4344 | | 0.4337 | 0.5 | 654 | 0.4250 | | 0.4346 | 0.75 | 981 | 0.4179 | | 0.3985 | 1.0 | 1308 | 0.4118 | | 0.3128 | 1.23 | 1635 | 0.4201 | | 0.3261 | 1.48 | 1962 | 0.4157 | | 0.3259 | 1.73 | 2289 | 0.4122 | | 0.3126 | 1.98 | 2616 | 0.4079 | | 0.2265 | 2.21 | 2943 | 0.4441 | | 0.2297 | 2.46 | 3270 | 0.4427 | | 0.2424 | 2.71 | 3597 | 0.4425 | - Transformers 4.40.0.dev0 - Pytorch 2.2.2+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0

Dolphin 3.0 Llama 3.1 8B 🐬 Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations [](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations Sponsors Our appreciation for the generous sponsors of Dolphin 3.0: - Crusoe Cloud - provided 16x L40s for training and evals - Akash - provided on-demand 8x H100 for training - Lazarus - provided 16x H100 for training - Cerebras - provided excellent and fast inference services for data labeling - Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi Respect and thanks to the creators of the open source datasets that were used: - OpenCoder-LLM (opc-sft-stage1, opc-sft-stage2) - microsoft (orca-agentinstruct-1M-v1, orca-math-word-problems-200k) - NousResearch (hermes-function-calling-v1) - AI-MO (NuminaMath-CoT, NuminaMath-TIR) - allenai (tulu-3-sft-mixture) - HuggingFaceTB (smoltalk) - m-a-p (CodeFeedback-Filtered-Instruction, Code-Feedback) Special thanks to - Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0. - RLHFlow for the excellent reward model used to filter the datasets - Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.

Website: https://dphn.ai Twitter: https://x.com/dphnAI Talk to Dolphin for free in our Web UI & Telegram bot Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot Our appreciation for the generous sponsors of Dolphin: - Lium - provided on-demand 8x H200s for testing and evaluation. - Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab Dolphin X1 8B is a result of our effort to directly uncensor Llama's 3.1 8B instruct while also keeping the same abilities or improving on them with finetuning. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. We maintained the default Llama-3 chat template for this model. A typical input would look like this In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi This model can be hosted using the vLLM engine, using the commands shown below: MMLU = 0.626900 MMLUPROFESSIONAL = 0.610200 MMLUCOLLEGE = 0.529400 MMLUHIGHSCHOOL = 0.691600 MMLUOTHER = 0.663700 IFEVAL = 0.608100 Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts

Website: https://dphn.ai Twitter: https://x.com/dphnAI Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot Dolphin Mistral 24B Venice Edition is a collaborative project we undert...

Website: https://dphn.ai Twitter: https://x.com/dphnAI Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot Dolphin Mistral 24B Venice Edition is a collaborative project we undertook with Venice.ai with the goal of creating the most uncensored version of Mistral 24B for use within the Venice ecosystem. Dolphin Mistral 24B Venice Edition is now live on https://venice.ai/ as “Venice Uncensored,” the new default model for all Venice users. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. We maintained Mistral's default chat template for this model. In this model, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. Example use of system prompt we used to get the model as uncensored as possible: Note: We recommond using a relatively low temperature, such as `temperature=0.15`. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi The model can be used with the following frameworks; - `vllm`: See here - `transformers`: See here We recommend using this model with the vLLM library to implement production-ready inference pipelines. Also make sure you have `mistralcommon >= 1.5.2` installed: You can also make use of a ready-to-go docker image or on the docker hub.

[](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations Dolphin-2.1-mistral-7b's training was sponsored by a16z. This model is based on mistralAI, with apache-2.0 license, so it is suitable for commercial or non-commercial use. This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly. This dataset is Dolphin, an open-source implementation of Microsoft's Orca I modified the dataset for uncensoring, deduping, cleaning, and quality. I added Jon Durbin's excellent Airoboros dataset to increase creativity. Training It took 48 hours to train 4 epochs on 4x A100s. Prompt format: This model (and all my future releases) use ChatML prompt format. Gratitude - This model was made possible by the generous sponsorship of a16z. - Thank you to Microsoft for authoring the Orca paper and inspiring this work. - Special thanks to Wing Lian, and TheBloke for helpful advice - And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework! - - Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way. Buy me a coffee Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric | Value | |-----------------------|---------------------------| | Avg. | 53.47 | | ARC (25-shot) | 64.42 | | HellaSwag (10-shot) | 84.92 | | MMLU (5-shot) | 63.32 | | TruthfulQA (0-shot) | 55.56 | | Winogrande (5-shot) | 77.74 | | GSM8K (5-shot) | 20.77 | | DROP (3-shot) | 7.56 |

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations [](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations Our appreciation for the sponsors of Dolphin 2.9.2: - Crusoe Cloud - provided excellent on-demand 8xH100 node This model is based on Qwen2-72b, and is governed by tongyi-qianwen license The base model has 128k context, and the full-weight fine-tuning was with 8k sequence length. This model was trained FFT on parameters selected by Laser Scanner, using ChatML prompt template format. Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly. Dolphin is licensed according to Qwen's tongyi-qianwen license. We grant permission for any use, including commercial, that falls within accordance with said license. Dolphin was trained on data generated from GPT4, among other models. Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric |Value| |-------------------|----:| |Avg. |32.00| |IFEval (0-Shot) |40.38| |BBH (3-Shot) |47.70| |MATH Lvl 5 (4-Shot)|21.37| |GPQA (0-shot) |16.00| |MuSR (0-shot) |17.04| |MMLU-PRO (5-shot) |49.52|

Dolphin 3.0 Llama 3.2 3B 🐬 Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations [](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations Sponsors Our appreciation for the generous sponsors of Dolphin 3.0: - Crusoe Cloud - provided 16x L40s for training and evals - Akash - provided on-demand 8x H100 for training - Lazarus - provided 16x H100 for training - Cerebras - provided excellent and fast inference services for data labeling - Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi Respect and thanks to the creators of the open source datasets that were used: - OpenCoder-LLM (opc-sft-stage1, opc-sft-stage2) - microsoft (orca-agentinstruct-1M-v1, orca-math-word-problems-200k) - NousResearch (hermes-function-calling-v1) - AI-MO (NuminaMath-CoT, NuminaMath-TIR) - allenai (tulu-3-sft-mixture) - HuggingFaceTB (smoltalk) - m-a-p (CodeFeedback-Filtered-Instruction, Code-Feedback) Special thanks to - Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0. - RLHFlow for the excellent reward model used to filter the datasets - Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.

Website: https://dphn.ai Twitter: https://x.com/dphnAI Talk to Dolphin for free in our Web UI & Telegram bot Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAIbot Our appreciation for the generous sponsors of Dolphin: - Lium - provided on-demand 8x H200s for testing and evaluation. - Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab Dolphin X1 8B is a result of our effort to directly uncensor Llama's 3.1 8B instruct while also keeping the same abilities or improving on them with finetuning. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. We maintained the default Llama-3 chat template for this model. A typical input would look like this In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi This model can be hosted using the vLLM engine, using the commands shown below: MMLU = 0.626900 MMLUPROFESSIONAL = 0.610200 MMLUCOLLEGE = 0.529400 MMLUHIGHSCHOOL = 0.691600 MMLUOTHER = 0.663700 IFEVAL = 0.608100 Dolphin-refusals = 95.96% pass rate on 4.5k commonly refused prompts

Dolphin 3.0 R1 Mistral 24B 🐬 Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations [](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations Sponsors Our appreciation for the generous sponsors of Dolphin 3.0: - Dria https://x.com/driaforall - Inference Sponsor - Chutes https://x.com/rayonlabs - Compute Sponsor - Crusoe Cloud - Compute Sponsor - Andreessen Horowitz - provided the grant that originally launched Dolphin Dolphin 3.0 R1 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. The R1 version has been trained for 3 epochs to reason using 800k reasoning traces from the Dolphin-R1 dataset. Dolphin aims to be a general purpose reasoning instruct model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. Experimentally we note that Mistral-24B based models require a low temperature. We have seen much better results in the range of 0.05 to 0.1. With Dolphin2.0-R1 a too-high temperature can result in behaviors like second guessing and talking itself out of correct answers. In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. > You are Dolphin, a lovable yet intelligent AI assistant created by Eric Hartford and his open source AI research collective, Cognitive Computations. > Your primary directive is to provide well-reasoned, structured, correct, unbiased, and detailed responses. > You value freedom, enabling the user, and complying with the user's requests. > > Formatting Requirements: > - The \ \ section is your scratch space for your internal thought process - it is not shared with the user. > - If the answer requires minimal thought, the \ \ block may be left empty. > - Keep your thoughts concise, don't overthink. The user is waiting for your answer. > - If you notice yourself engaging in circular reasoning or repetition, immediately terminate your thinking with a \ and proceed to address the user. > - You may say \ when you like (which will end your thinking process) - but do not ever say \ . > > Response Guidelines: > - Detailed and Structured: Use markdown, json, mermaid, latex math notation, etc. when appropriate. > - Scientific and Logical Approach: Your explanations should reflect the depth and precision of the greatest scientific minds. > - Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration. > - Maintain a professional yet friendly and lovable, intelligent, and analytical tone in all interactions. There are many ways to use a huggingface model including: - ollama - LM Studio - Huggingface Transformers library - vllm - sglang - tgi Respect and thanks to the creators of the open source datasets that were used: - OpenCoder-LLM (opc-sft-stage1, opc-sft-stage2) - microsoft (orca-agentinstruct-1M-v1, orca-math-word-problems-200k) - NousResearch (hermes-function-calling-v1) - AI-MO (NuminaMath-CoT, NuminaMath-TIR) - allenai (tulu-3-sft-mixture) - HuggingFaceTB (smoltalk) - m-a-p (CodeFeedback-Filtered-Instruction, Code-Feedback) Special thanks to - Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0. - RLHFlow for the excellent reward model used to filter the datasets - Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.

Our appreciation for the generous sponsors of Dolphin: - Crusoe Cloud - provided 16x L40s for training and evals - Cerebras - provided excellent and fast inference services for data labeling - Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab Dolphin Llama 3.1 8B Instruct is a result of our effort to directly uncensor Llama's 3.1 8B instruct-tuned model. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin. We maintained the default Llama chat template for this model. In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them. Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want. There are many ways to use a huggingface model including: