Upload GGUF model

README.md

@@ -1,18 +1,6 @@
----
-license: apache-2.0
-datasets:
-- dcruver/keip-assistant-dataset
-language:
-- en
-metrics:
-- accuracy
-base_model:
-- Qwen/Qwen3-8B
-pipeline_tag: text-generation
----
-# keip-assistant.q4_k_m.gguf - GGUF
+# lora-merged - GGUF
 
-This is a GGUF version of the lora-merged model, trained on [dcruver/keip-assistant-dataset](https://huggingface.co/dcruver/keip-assistant-dataset)
+This is a GGUF version of the lora-merged model.
 
 ## Model Details
 
@@ -22,4 +10,9 @@ This is a GGUF version of the lora-merged model, trained on [dcruver/keip-assist
 
 ## Usage
 
-This model can be used with [keip-canvas](https://github.com/OctoConsulting/keip-canvas). View the documentation on that project for how it's intended to be used.
+This model can be used with [llama.cpp](https://github.com/ggerganov/llama.cpp) and compatible applications.
+
+```bash
+# Example llama.cpp command
+./main -m keip-assistant.q4_k_m.gguf -n 1024 -p "Your prompt here"
+```

keip-assistant.q4_k_m.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e95f84b0321296332cbd5fa5c6f577d0dece39495943f1f4bfefb42c197081
+oid sha256:4d078a7435aeb42e149271bc4ff75a3488fd17648fba059d51623ecca98316b1
 size 5027783392