feat: add Q4_K_M gguf for Ollama / llama.cpp consumers

Converted from model.safetensors via llama.cpp convert_hf_to_gguf.py
(bf16 intermediate), then quantized with llama-quantize to Q4_K_M.
File naming matches the convention used by lthn/lemer so Ollama's HF
pull integration works: 'ollama pull hf.co/LetheanNetwork/lemer:q4_k_m'.

Sized: ~3.2G (bf16 source was 9.3G).

Co-Authored-By: Virgil <virgil@lethean.io>

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

lemer-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51adbd5c0c2966cf252102dc10a38fdfa5e3f977abd9967ae6b5db9208048ca
+size 3427873472