diff --git a/.nojekyll b/.nojekyll index a212cdfb4..5c8642207 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -9ba8a312 \ No newline at end of file +55eb0ba3 \ No newline at end of file diff --git a/docs/dataset-formats/conversation.html b/docs/dataset-formats/conversation.html index 49c118edb..8cd975aae 100644 --- a/docs/dataset-formats/conversation.html +++ b/docs/dataset-formats/conversation.html @@ -291,6 +291,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
  • pygmalion
  • sharegpt.load_role
  • sharegpt.load_guanaco
    • +
  • sharegpt.load_ultrachat
  • sharegpt_jokes
    • @@ -373,6 +374,16 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin 
    {"conversations": [{"from": "...", "value": "..."}]}
    +
    +

    sharegpt.load_ultrachat

    +

    conversations where the turns field is ‘messages’, human is ‘user’ and gpt is ‘assistant’.

    +
    +
    +
    data.jsonl
    +
    +
    {"messages": [{"user": "...", "assistant": "..."}]}
    +
    +

    sharegpt_jokes

    creates a chat where bot is asked to tell a joke, then explain why the joke is funny

    @@ -380,7 +391,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin 
    data.jsonl
    -
    {"conversations": [{"title": "...", "text": "...", "explanation": "..."}]}
    +
    {"conversations": [{"title": "...", "text": "...", "explanation": "..."}]}
    diff --git a/docs/dataset-formats/index.html b/docs/dataset-formats/index.html index 142606eb1..2099356d4 100644 --- a/docs/dataset-formats/index.html +++ b/docs/dataset-formats/index.html @@ -357,7 +357,7 @@ Description - + Pre-training @@ -365,7 +365,7 @@ Description Data format for a pre-training completion task. - + Instruction Tuning @@ -373,7 +373,7 @@ Description Instruction tuning formats for supervised fine-tuning. - + Conversation @@ -381,7 +381,7 @@ Description Conversation format for supervised fine-tuning. - + Template-Free @@ -389,7 +389,7 @@ Description Construct prompts without a template. - + Custom Pre-Tokenized Dataset diff --git a/search.json b/search.json index 863e68ac2..99bbaf021 100644 --- a/search.json +++ b/search.json @@ -98,6 +98,17 @@ "Conversation" ] }, + { + "objectID": "docs/dataset-formats/conversation.html#sharegpt.load_ultrachat", + "href": "docs/dataset-formats/conversation.html#sharegpt.load_ultrachat", + "title": "Conversation", + "section": "sharegpt.load_ultrachat", + "text": "sharegpt.load_ultrachat\nconversations where the turns field is ‘messages’, human is ‘user’ and gpt is ‘assistant’.\n\n\ndata.jsonl\n\n{\"messages\": [{\"user\": \"...\", \"assistant\": \"...\"}]}", + "crumbs": [ + "Dataset Formats", + "Conversation" + ] + }, { "objectID": "docs/dataset-formats/conversation.html#sharegpt_jokes", "href": "docs/dataset-formats/conversation.html#sharegpt_jokes", diff --git a/sitemap.xml b/sitemap.xml index f7efcb0c1..f8ce6481a 100644 --- a/sitemap.xml +++ b/sitemap.xml @@ -2,98 +2,98 @@ https://axolotl-ai-cloud.github.io/axolotl/docs/config.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/tokenized.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/pretraining.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/fsdp_qlora.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/mac.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/nccl.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/unsloth.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/examples/colab-notebooks/colab-axolotl-example.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/FAQS.html - 2024-08-05T16:42:29.797Z + 2024-08-05T17:12:16.923Z https://axolotl-ai-cloud.github.io/axolotl/index.html - 2024-08-05T16:42:29.813Z + 2024-08-05T17:12:16.939Z https://axolotl-ai-cloud.github.io/axolotl/TODO.html - 2024-08-05T16:42:29.797Z + 2024-08-05T17:12:16.923Z https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/torchao.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/input_output.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset_preprocessing.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/rlhf.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/index.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/template_free.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html - 2024-08-05T16:42:29.801Z + 2024-08-05T17:12:16.927Z