Update README.md

README.md

@@ -1,3 +1,23 @@
----
-license: llama3
----
+---
+license: llama3
+tags:
+- java
+- llama
+- llama3
+- gguf
+- llama3.java
+---
+
+## GGUF models for llama3.java
+Pure .gguf `Q4_0` and `Q8_0` quantizations of Llama 3 8B instruct, ready to consume by [llama3.java](https://github.com/mukel/llama3.java).
+
+In the wild, `Q8_0` quantizations are fine, but `Q4_0` quantizations are rarely pure e.g. the `output.weights` tensor is quantized with `Q6_K`, instead of `Q4_0`.  
+A pure `Q4_0` quantization can be generated from a high precision (F32, F16, BFLOAT16) .gguf source with the quantize utility from llama.cpp as follows:
+
+```
+./quantize --pure ./Meta-Llama-3-8B-Instruct-F32.gguf ./Meta-Llama-3-8B-Instruct-Q4_0.gguf Q4_0
+```
+
+## Model Details
+
+Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.