Add 5-bit GGUF + initial card

.gguf file and 5-bit Quantized .gguf file

.gitattributes

@@ -1,35 +1,37 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+medgemma-4b-it-finnetunned-merged_f16.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-it-finnetunned-merged_new_for_cpu_q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,35 @@
+# MedGemma 4B (Q5_K_M) — CPU Space
+Loads GGUF from `USERNAME/medgemma-4b-it-medical-gguf` and serves a Gradio chat on free cpu-basic.
 ---
-license: gemma
+license: other  # ← check base model’s license terms and choose correctly
+base_model: google/medgemma-4b-it        # or the exact base you fine-tuned
+tags:
+  - gguf
+  - llama.cpp
+  - quantized
+  - q5_k_m
+  - medical
+  - chat
+library_name: llama.cpp
+inference: false
 ---
+
+# medgemma-4b-it — medical fine-tune (5-bit GGUF)
+
+## Files
+- `medgemma-4b-it-finnetunned-merged_new_for_cpu_q5_k_m.gguf` (~2.83 GB)
+
+## Intended use
+(Describe task/domain, safety notes, dataset or method you used to fine-tune.)
+
+## How to run (llama.cpp)
+```bash
+# Requires llama.cpp. You can run directly from the Hub path:
+llama-cli -m hf://USERNAME/medgemma-4b-it-medical-gguf/medgemma-4b-it-finnetunned-merged_new_for_cpu_q5_k_m.gguf -p "Hello"
+
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+p = hf_hub_download("USERNAME/medgemma-4b-it-medical-gguf",
+                    "medgemma-4b-it-finnetunned-merged_new_for_cpu_q5_k_m.gguf")
+llm = Llama(model_path=p, n_ctx=4096, n_threads=8, chat_format="gemma")
+print(llm.create_chat_completion(messages=[{"role":"user","content":"Hello"}]))

medgemma-4b-it-finnetunned-merged_f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a744b064d38ceab39f5b582d3adb44d9e779a775d8421fefd538acdde17078
+size 7767803488

medgemma-4b-it-finnetunned-merged_new_for_cpu_q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05709bc47096c04aded6b5e480475604683b08e6c9f51ce2a193036514e95134
+size 2829697888