Skip to content

Distribute and run LLMs with a single file.

Add links to example wrapped weights

Stephen Hood638d7472d06f
diff --git a/README.md b/README.md
index 7071b826..5955f7ce 100644
--- a/README.md
+++ b/README.md
@@ -63,6 +63,17 @@ sudo wget -O /usr/bin/ape https://cosmo.zip/pub/cosmos/bin/ape-$(uname -m).elf
sudo sh -c "echo ':APE:M::MZqFpD::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"
sudo sh -c "echo ':APE-jart:M::jartsr::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"
```
+### Example wrapped weights
+
+We also provide example binaries that embed several different models. You can download these from Hugging Face via the links below. "Command-line binaries" run from the command line, just as if you were invoking llama.cpp's "main" function manually. "Server binaries" launch a local web server (at 127.0.0.1:8080) that provides a web-based chatbot UI.
+
+| Model | Command-line binary | Server binary |
+| --- | --- | --- |
+| Mistral-7B-Instruct | [mistral-7b-instruct-v0.1-Q4_K_M-main.llamafile (4.4 GB)](https://huggingface.co/jartine/mistral-7b.llamafile/resolve/main/mistral-7b-instruct-v0.1-Q4_K_M-main.llamafile?download=true) | [mistral-7b-instruct-v0.1-Q4_K_M-server.llamafile (4.4 GB)](https://huggingface.co/jartine/mistral-7b.llamafile/resolve/main/mistral-7b-instruct-v0.1-Q4_K_M-server.llamafile?download=true) |
+| LLaVA 1.5 | (Not provided because this model's features are best utilized via the web UI) | [llava-v1.5-7b-q4-server.llamafile (4.3 GB)](https://huggingface.co/jartine/llava-v1.5-7B-GGUF/resolve/main/llava-v1.5-7b-q4-server.llamafile?download=true) |
+| WizardCoder-Python-13B | [wizardcoder-python-13b-main.llamafile (7.9 GB)](https://huggingface.co/jartine/wizardcoder-13b-python/resolve/main/wizardcoder-python-13b-main.llamafile?download=true) | [wizardcoder-python-13b-server.llamafile (7.9GB)](https://huggingface.co/jartine/wizardcoder-13b-python/resolve/main/wizardcoder-python-13b-server.llamafile?download=true) |
+
+
### GPU Support