Instructions to use Haongchen/MemoryVLA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Piper
How to use Haongchen/MemoryVLA with Piper:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Document Llama metadata-only dependency
Browse files
base_models/llama-2-7b-hf/README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Llama-2 7B Metadata
|
| 2 |
+
|
| 3 |
+
This directory contains only the configuration and tokenizer metadata needed to instantiate the Llama-2 architecture and tokenize instructions for MemoryVLA inference.
|
| 4 |
+
|
| 5 |
+
The full Llama-2 parameter weights are not mirrored here. The MemoryVLA task checkpoint contains the trained `llm_backbone` parameters; set `MEMORYVLA_SKIP_BASE_WEIGHTS=1` and point `MEMORYVLA_LLAMA2_7B_PATH` to this directory after downloading it.
|
| 6 |
+
|
| 7 |
+
Use remains subject to the applicable Llama-2 license and access terms.
|