more link fixes (run-llama#19929)

Author: logan-markewich

docs/docs/module_guides/models/llms/modules.md

@@ -2,63 +2,63 @@
 
 We support integrations with OpenAI, Anthropic, Google, Hugging Face, and more.
 
-- [AI21](/python/examples/llm/ai21.ipynb)
-- [Anthropic](/python/examples/llm/anthropic.ipynb)
-- [AnyScale](/python/examples/llm/anyscale.ipynb)
-- [ASI](/python/examples/llm/asi1.ipynb)
-- [Azure OpenAI](/python/examples/llm/azure_openai.ipynb)
-- [Baseten](/python/examples/llm/baseten.ipynb)
-- [Bedrock](/python/examples/llm/bedrock.ipynb)
-- [Clarifai](/python/examples/llm/clarifai.ipynb)
-- [Cleanlab](/python/examples/llm/cleanlab.ipynb)
-- [Cohere](/python/examples/llm/cohere.ipynb)
-- [CometAPI](/python/examples/llm/cometapi.ipynb)
-- [Dashscope](/python/examples/llm/dashscope.ipynb)
-- [Dashscope Multi-Modal](/python/examples/multi_modal/dashscope_multi_modal.ipynb)
-- [EverlyAI](/python/examples/llm/everlyai.ipynb)
-- [Featherless AI](/python/examples/llm/featherlessai.ipynb)
-- [Fireworks](/python/examples/llm/fireworks.ipynb)
-- [Friendli](/python/examples/llm/friendli.ipynb)
-- [Google Gen AI](/python/examples/llm/google_genai.ipynb)
-- [Gradient](/python/examples/llm/gradient_base_model.ipynb)
-- [Gradient Model Adapter](/python/examples/llm/gradient_model_adapter.ipynb)
-- [Groq](/python/examples/llm/groq.ipynb)
-- [Heroku](/python/examples/llm/heroku.ipynb)
-- [HuggingFace Camel-7B](/python/examples/customization/llms/SimpleIndexDemo-Huggingface_camel.ipynb)
-- [HuggingFace StableLM](/python/examples/customization/llms/SimpleIndexDemo-Huggingface_stablelm.ipynb)
-- [HuggingFace Llama2](/python/examples/vector_stores/SimpleIndexDemoLlama-Local.ipynb)
-- [Konko](/python/examples/llm/konko.ipynb)
-- [LangChain](/python/examples/llm/langchain.ipynb)
-- [LiteLLM](/python/examples/llm/litellm.ipynb)
-- [Llama API](/python/examples/llm/llama_api.ipynb)
-- [Llama CPP](/python/examples/llm/llama_cpp.ipynb)
-- [LocalAI](/python/examples/llm/localai.ipynb)
-- [MariTalk](/python/examples/llm/maritalk.ipynb)
-- [MistralAI](/python/examples/llm/mistralai.ipynb)
-- [Modelscope](/python/examples/llm/modelscope.ipynb)
-- [MonsterAPI](/python/examples/llm/monsterapi.ipynb)
-- [MyMagic](/python/examples/llm/mymagic.ipynb)
-- [NeutrinoAI](/python/examples/llm/neutrino.ipynb)
-- [Nebius AI](/python/examples/llm/nebius.ipynb)
-- [Nvidia TensorRT-LLM](/python/examples/llm/nvidia_tensorrt.ipynb)
-- [Nvidia Triton](/python/examples/llm/nvidia_triton.ipynb)
-- [Ollama](/python/examples/llm/ollama.ipynb)
-- [OpenAI](/python/examples/llm/openai.ipynb)
-- [OpenRouter](/python/examples/llm/openrouter.ipynb)
-- [Perplexity](/python/examples/llm/perplexity.ipynb)
-- [Pipeshift](/python/examples/llm/pipeshift.ipynb)
-- [PremAI](/python/examples/llm/premai.ipynb)
-- [Portkey](/python/examples/llm/portkey.ipynb)
-- [Predibase](/python/examples/llm/predibase.ipynb)
-- [Replicate Llama2](/python/examples/llm/llama_2.ipynb)
-- [Replicate Vicuna](/python/examples/llm/vicuna.ipynb)
-- [Replicate Vector Index Llama2](/python/examples/vector_stores/SimpleIndexDemoLlama2.ipynb)
-- [RunGPT](/python/examples/llm/rungpt.ipynb)
-- [SageMaker](/python/examples/llm/sagemaker_endpoint_llm.ipynb)
-- [SambaNova Systems](/python/examples/llm/sambanovasystems.ipynb)
-- [Together.ai](/python/examples/llm/together.ipynb)
-- [Upstage](/python/examples/llm/upstage.ipynb)
-- [Vercel AI Gateway](/python/examples/llm/vercel-ai-gateway.ipynb)
-- [vLLM](/python/examples/llm/vllm.ipynb)
-- [Xorbits Inference](/python/examples/llm/xinference_local_deployment.ipynb)
-- [Yi](/python/examples/llm/yi.ipynb)
+- [AI21](/python/examples/llm/ai21)
+- [Anthropic](/python/examples/llm/anthropic)
+- [AnyScale](/python/examples/llm/anyscale)
+- [ASI](/python/examples/llm/asi1)
+- [Azure OpenAI](/python/examples/llm/azure_openai)
+- [Baseten](/python/examples/llm/baseten)
+- [Bedrock](/python/examples/llm/bedrock)
+- [Clarifai](/python/examples/llm/clarifai)
+- [Cleanlab](/python/examples/llm/cleanlab)
+- [Cohere](/python/examples/llm/cohere)
+- [CometAPI](/python/examples/llm/cometapi)
+- [Dashscope](/python/examples/llm/dashscope)
+- [Dashscope Multi-Modal](/python/examples/multi_modal/dashscope_multi_modal)
+- [EverlyAI](/python/examples/llm/everlyai)
+- [Featherless AI](/python/examples/llm/featherlessai)
+- [Fireworks](/python/examples/llm/fireworks)
+- [Friendli](/python/examples/llm/friendli)
+- [Google Gen AI](/python/examples/llm/google_genai)
+- [Gradient](/python/examples/llm/gradient_base_model)
+- [Gradient Model Adapter](/python/examples/llm/gradient_model_adapter)
+- [Groq](/python/examples/llm/groq)
+- [Heroku](/python/examples/llm/heroku)
+- [HuggingFace Camel-7B](/python/examples/customization/llms/SimpleIndexDemo-Huggingface_camel)
+- [HuggingFace StableLM](/python/examples/customization/llms/SimpleIndexDemo-Huggingface_stablelm)
+- [HuggingFace Llama2](/python/examples/vector_stores/SimpleIndexDemoLlama-Local)
+- [Konko](/python/examples/llm/konko)
+- [LangChain](/python/examples/llm/langchain)
+- [LiteLLM](/python/examples/llm/litellm)
+- [Llama API](/python/examples/llm/llama_api)
+- [Llama CPP](/python/examples/llm/llama_cpp)
+- [LocalAI](/python/examples/llm/localai)
+- [MariTalk](/python/examples/llm/maritalk)
+- [MistralAI](/python/examples/llm/mistralai)
+- [Modelscope](/python/examples/llm/modelscope)
+- [MonsterAPI](/python/examples/llm/monsterapi)
+- [MyMagic](/python/examples/llm/mymagic)
+- [NeutrinoAI](/python/examples/llm/neutrino)
+- [Nebius AI](/python/examples/llm/nebius)
+- [Nvidia TensorRT-LLM](/python/examples/llm/nvidia_tensorrt)
+- [Nvidia Triton](/python/examples/llm/nvidia_triton)
+- [Ollama](/python/examples/llm/ollama)
+- [OpenAI](/python/examples/llm/openai)
+- [OpenRouter](/python/examples/llm/openrouter)
+- [Perplexity](/python/examples/llm/perplexity)
+- [Pipeshift](/python/examples/llm/pipeshift)
+- [PremAI](/python/examples/llm/premai)
+- [Portkey](/python/examples/llm/portkey)
+- [Predibase](/python/examples/llm/predibase)
+- [Replicate Llama2](/python/examples/llm/llama_2)
+- [Replicate Vicuna](/python/examples/llm/vicuna)
+- [Replicate Vector Index Llama2](/python/examples/vector_stores/SimpleIndexDemoLlama2)
+- [RunGPT](/python/examples/llm/rungpt)
+- [SageMaker](/python/examples/llm/sagemaker_endpoint_llm)
+- [SambaNova Systems](/python/examples/llm/sambanovasystems)
+- [Together.ai](/python/examples/llm/together)
+- [Upstage](/python/examples/llm/upstage)
+- [Vercel AI Gateway](/python/examples/llm/vercel-ai-gateway)
+- [vLLM](/python/examples/llm/vllm)
+- [Xorbits Inference](/python/examples/llm/xinference_local_deployment)
+- [Yi](/python/examples/llm/yi)

docs/docs/optimizing/fine-tuning/fine-tuning.md

@@ -58,7 +58,7 @@ We then launch a finetuning job, and get back a distilled model. We can evaluate
 
 - [GPT-3.5 Fine-tuning Notebook (Colab)](https://colab.research.google.com/drive/1NgyCJVyrC2xcZ5lxt2frTU862v6eJHlc?usp=sharing)
 - [GPT-3.5 Fine-tuning Notebook (Notebook link)](/python/examples/finetuning/openai_fine_tuning)
-- [[WIP] Function Calling Fine-tuning](/python/examples/finetuning/openai_fine_tuning_functions.ipynb)
+- [[WIP] Function Calling Fine-tuning](/python/examples/finetuning/openai_fine_tuning_functions)
 
 **Old**
 

docs/docs/use_cases/fine_tuning.md

@@ -58,7 +58,7 @@ We then launch a finetuning job, and get back a distilled model. We can evaluate
 
 - [GPT-3.5 Fine-tuning Notebook (Colab)](https://colab.research.google.com/drive/1NgyCJVyrC2xcZ5lxt2frTU862v6eJHlc?usp=sharing)
 - [GPT-3.5 Fine-tuning Notebook (Notebook link)](/python/examples/finetuning/openai_fine_tuning)
-- [[WIP] Function Calling Fine-tuning](/python/examples/finetuning/openai_fine_tuning_functions.ipynb)
+- [[WIP] Function Calling Fine-tuning](/python/examples/finetuning/openai_fine_tuning_functions)
 
 **Old**