Update README.md

README.md

@@ -1,3 +1,36 @@
----
-license: apache-2.0
----
+---
+library_name: yi.java
+license: apache-2.0
+base_model: 01-ai/Yi-Coder-9B-Chat
+pipeline_tag: text-generation
+quantized_by: mukel
+tags:
+- java
+- yi
+- llama3.java
+- yi.java
+- code
+---
+
+# GGUF models for yi.java
+Pure .gguf `Q4_0` and `Q8_0` quantizations of 01.ai Yi models, ready to consume by [yi.java](https://github.com/mukel/yi.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 `llama-quantize` utility from llama.cpp as follows:
+
+```
+./llama-quantize --pure ./Yi-Coder-9B-Chat-F32.gguf ./Yi-Coder-9B-Chat-Q4_0.gguf Q4_0
+```
+
+# Intro
+
+Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters. 
+
+Key features:
+- Excelling in long-context understanding with a maximum context length of 128K tokens.
+- Supporting 52 major programming languages:
+```bash
+  'java', 'markdown', 'python', 'php', 'javascript', 'c++', 'c#', 'c', 'typescript', 'html', 'go', 'java_server_pages', 'dart', 'objective-c', 'kotlin', 'tex', 'swift', 'ruby', 'sql', 'rust', 'css', 'yaml', 'matlab', 'lua', 'json', 'shell', 'visual_basic', 'scala', 'rmarkdown', 'pascal', 'fortran', 'haskell', 'assembly', 'perl', 'julia', 'cmake', 'groovy', 'ocaml', 'powershell', 'elixir', 'clojure', 'makefile', 'coffeescript', 'erlang', 'lisp', 'toml', 'batchfile', 'cobol', 'dockerfile', 'r', 'prolog', 'verilog'
+  ```
+
+For model details and benchmarks, see [Yi-Coder blog](https://01-ai.github.io/) and [Yi-Coder README](https://github.com/01-ai/Yi-Coder).