From 4b7e11bd310af870df026f16a2837269d2b2d82d Mon Sep 17 00:00:00 2001 From: Vaibhav Srivastav Date: Wed, 20 Dec 2023 20:27:13 +0530 Subject: [PATCH] Add URLs to HF MLX-Community org. (#153) * up * Add ref to MLX org on the README. * nit: language. * Standardise org name. --- README.md | 2 ++ llama/README.md | 6 ++---- mistral/README.md | 3 +++ phi2/README.md | 3 +++ 4 files changed, 10 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 5ea53d25..da2aa90c 100644 --- a/README.md +++ b/README.md @@ -16,6 +16,8 @@ Some more useful examples include: - Bidirectional language understanding with [BERT](bert) - Semi-supervised learning on graph-structured data with [GCN](gcn). +Note: You can now directly download a few converted checkpoints from the [MLX Community](https://huggingface.co/mlx-community) organisation on Hugging Face. + ## Contributing We are grateful for all of [our diff --git a/llama/README.md b/llama/README.md index 39c0267c..0bd6d5af 100644 --- a/llama/README.md +++ b/llama/README.md @@ -20,10 +20,8 @@ weights you will need to request access from Meta: - [Request Llama v1](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform) - [Request Llama v2](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) - -Alternatively, you can also download a select converted checkpoints from the -[mlx-llama](https://huggingface.co/mlx-llama) community organisation on Hugging -Face and skip the conversion step. +> [!TIP] +> Alternatively, you can also download a few converted checkpoints from the the [MLX Community](https://huggingface.co/mlx-community) organisation on Hugging Face and skip the conversion step. You can download the TinyLlama models directly from [Hugging Face](https://huggingface.co/TinyLlama). diff --git a/mistral/README.md b/mistral/README.md index c2406b6d..5b9bcbae 100644 --- a/mistral/README.md +++ b/mistral/README.md @@ -28,6 +28,9 @@ python convert.py The conversion script will save the converted weights in the same location. +> [!TIP] +> Alternatively, you can also download a few converted checkpoints from the the [MLX Community](https://huggingface.co/mlx-community) organisation on Hugging Face and skip the conversion step. + ### Run Once you've converted the weights to MLX format, you can generate text with diff --git a/phi2/README.md b/phi2/README.md index f5d80696..4729257a 100644 --- a/phi2/README.md +++ b/phi2/README.md @@ -17,6 +17,9 @@ python convert.py This will make the `weights.npz` file which MLX can read. +> [!TIP] +> Alternatively, you can also download a few converted checkpoints from the the [MLX Community](https://huggingface.co/mlx-community) organisation on Hugging Face and skip the conversion step. + ## Generate To generate text with the default prompt: