Add GGUF quantizations (Q8_0, Q4_K_M)

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Eve-2-MoE-NanoExtract-272M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Eve-2-MoE-NanoExtract-272M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Eve-2-MoE-NanoExtract-272M-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0f4cf0a077532f0a7e01a5c3b6cef47e2dcd862a071b66d985678acd12a0b2
+size 189484672

Eve-2-MoE-NanoExtract-272M-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5441b04a744ed29029fae5a079b5dd3357361a1b2aca59d65d14ab47da246a51
+size 290929792

README.md

@@ -0,0 +1,46 @@
+---
+base_model: anthonym21/Eve-2-MoE-NanoExtract-272M
+tags:
+  - gguf
+  - quantized
+  - moe
+  - eve-2
+license: apache-2.0
+---
+
+# Eve-2-MoE-NanoExtract-272M - GGUF
+
+GGUF quantizations of [anthonym21/Eve-2-MoE-NanoExtract-272M](https://huggingface.co/anthonym21/Eve-2-MoE-NanoExtract-272M).
+
+## Quantization Variants
+
+| Quantization | Filename | Size |
+|---|---|---|
+| Q8_0 | Eve-2-MoE-NanoExtract-272M-Q8_0.gguf | 290.9 MB |
+| Q4_K_M | Eve-2-MoE-NanoExtract-272M-Q4_K_M.gguf | 189.5 MB |
+
+## Usage with Ollama
+
+```bash
+ollama run anthonym21/eve-2-moe-nanoextract-272m
+```
+
+## Usage with llama.cpp
+
+```bash
+llama-cli -m Eve-2-MoE-NanoExtract-272M-Q4_K_M.gguf -p "Your prompt here"
+```
+
+## Architecture
+
+- **Type**: DeepSeek-style Mixture of Experts (MoE)
+- **Parameters**: 272M total
+- **Layers**: 12
+- **Hidden dim**: 512
+- **Experts**: 8 routed (top-2) + 1 shared per layer
+- **Context**: 2048 tokens
+- **Tokenizer**: GPT-2
+
+## Parent Model
+
+This is a quantized version of [anthonym21/Eve-2-MoE-NanoExtract-272M](https://huggingface.co/anthonym21/Eve-2-MoE-NanoExtract-272M).