Upload 2 files

README.md

@@ -94,9 +94,25 @@ llama-cli -m loom-spark-f32.gguf \
   -p "<tools:off>\n<user> who are you?\n<loom>" -n 128 --temp 0.85 --top-k 50
 ```
 
+## Option B2 — Ollama
+
+The default Ollama template does NOT fit this model (it will ramble). Use the
+Modelfile shipped in `ollama/`:
+
+```bash
+ollama pull hf.co/textilelabs/Loom-Spark
+ollama create loom-spark -f Modelfile     # from the ollama/ folder of this repo
+ollama run loom-spark "hi"
+```
+
+That gives the offline persona: greetings, identity, honest deferrals. If a
+reply ends in a `<lookup>…</lookup>` line, that's the model saying *"I'd search
+for this"* — raw runners can't execute searches; for real internet answers use
+the harness (Option C).
+
 Note: without a wrapper that executes `<lookup>` calls and splices `<result>`
-blocks back in, GGUF runners get the model's honest "I don't know, but here's
-what I'd look up" side. That is by design.
+blocks back in, GGUF/Ollama runners get the model's honest "I don't know, but
+here's what I'd look up" side. That is by design.
 
 ## Option C — the harness (with internet)
 

ollama/Modelfile

@@ -0,0 +1,10 @@
+FROM hf.co/textilelabs/Loom-Spark
+TEMPLATE """<tools:off>
+<user> {{ .Prompt }}
+<loom>"""
+PARAMETER stop "<|endoftext|>"
+PARAMETER stop "<user>"
+PARAMETER stop "<result>"
+PARAMETER temperature 0.85
+PARAMETER top_k 50
+PARAMETER num_predict 160