You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+27-2Lines changed: 27 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# Llama Recipes: Examples to get started using the Llama models from Meta
2
2
<!-- markdown-link-check-disable -->
3
-
The 'llama-recipes' repository is a companion to the [Meta Llama](https://github.com/meta-llama/llama-models) models. We support the latest version, [Llama 3.1](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), in this repository. The goal is to provide a scalable library for fine-tuning Meta Llama models, along with some example scripts and notebooks to quickly get started with using the models in a variety of use-cases, including fine-tuning for domain adaptation and building LLM-based applications with Llama and other tools in the LLM ecosystem. The examples here showcase how to run Llama locally, in the cloud, and on-prem.
3
+
The 'llama-recipes' repository is a companion to the [Meta Llama](https://github.com/meta-llama/llama-models) models. We support the latest version, [Llama 3.1](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), in this repository. The goal is to provide a scalable library for fine-tuning Meta Llama models, along with some example scripts and notebooks to quickly get started with using the models in a variety of use-cases, including fine-tuning for domain adaptation and building LLM-based applications with Llama and other tools in the LLM ecosystem. The examples here showcase how to run Llama locally, in the cloud, and on-prem.
4
4
5
5
<!-- markdown-link-check-enable -->
6
6
> [!IMPORTANT]
@@ -31,7 +31,7 @@ The 'llama-recipes' repository is a companion to the [Meta Llama](https://github
31
31
> ```
32
32
> Each message gets trailed by an `<|eot_id|>` token before a new header is started, signaling a role change.
33
33
>
34
-
> More details on the new tokenizer and prompt template can be found [here](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1).
34
+
> More details on the new tokenizer and prompt template can be found [here](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1).
35
35
36
36
>
37
37
> [!NOTE]
@@ -55,6 +55,7 @@ The 'llama-recipes' repository is a companion to the [Meta Llama](https://github
@@ -160,6 +161,30 @@ Contains modules which support the example recipes:
160
161
|[utils](src/llama_recipes/utils/)| Utility files for:<br/> - `train_utils.py` provides training/eval loop and more train utils.<br/> - `dataset_utils.py` to get preprocessed datasets.<br/> - `config_utils.py` to override the configs received from CLI.<br/> - `fsdp_utils.py` provides FSDP wrapping policy for PEFT methods.<br/> - `memory_utils.py` context manager to track different memory stats in train loop. |
161
162
162
163
164
+
## Supported Features
165
+
The recipes and modules in this repository support the following features:
Copy file name to clipboardExpand all lines: recipes/quickstart/README.md
+4-24Lines changed: 4 additions & 24 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,28 +2,8 @@
2
2
3
3
If you are new to developing with Meta Llama models, this is where you should start. This folder contains introductory-level notebooks across different techniques relating to Meta Llama.
4
4
5
-
* The [Running_Llama3_Anywhere](./Running_Llama3_Anywhere/) notebooks demonstrate how to run Llama inference across Linux, Mac and Windows platforms using the appropriate tooling.
6
-
* The [Prompt_Engineering_with_Llama_3](./Prompt_Engineering_with_Llama_3.ipynb) notebook showcases the various ways to elicit appropriate outputs from Llama. Take this notebook for a spin to get a feel for how Llama responds to different inputs and generation parameters.
5
+
* The [Running_Llama_Anywhere](./Running_Llama3_Anywhere/) notebooks demonstrate how to run Llama inference across Linux, Mac and Windows platforms using the appropriate tooling.
6
+
* The [Prompt_Engineering_with_Llama](./Prompt_Engineering_with_Llama_3.ipynb) notebook showcases the various ways to elicit appropriate outputs from Llama. Take this notebook for a spin to get a feel for how Llama responds to different inputs and generation parameters.
7
7
* The [inference](./inference/) folder contains scripts to deploy Llama for inference on server and mobile. See also [3p_integrations/vllm](../3p_integrations/vllm/) and [3p_integrations/tgi](../3p_integrations/tgi/) for hosting Llama on open-source model servers.
8
-
* The [RAG](./RAG/) folder contains a simple Retrieval-Augmented Generation application using Llama 3.
9
-
* The [finetuning](./finetuning/) folder contains resources to help you finetune Llama 3 on your custom datasets, for both single- and multi-GPU setups. The scripts use the native llama-recipes finetuning code found in [finetuning.py](../../src/llama_recipes/finetuning.py) which supports these features:
| FSDP checkpoint conversion to HF for inference | ✅ |
29
-
| W&B experiment tracker | ✅ |
8
+
* The [RAG](./RAG/) folder contains a simple Retrieval-Augmented Generation application using Llama.
9
+
* The [finetuning](./finetuning/) folder contains resources to help you finetune Llama on your custom datasets, for both single- and multi-GPU setups. The scripts use the native llama-recipes finetuning code found in [finetuning.py](../../src/llama_recipes/finetuning.py) which supports these features:
0 commit comments