Upload Modelfile with huggingface_hub

Modelfile

@@ -10,29 +10,21 @@
 # 2) ollama create stcoder-qwen25-7b:<quant> -f Modelfile     e.g. ollama create stcoder-qwen25-7b:q8_0 -f Modelfile
 # 3) ollama run stcoder-qwen25-7b:<quant> "Motor starts 5 seconds after the start button; stop and E-stop drop it."
 #
-# Requires Ollama 0.3 or newer.
+# Requires Ollama 0.3 or newer; verified on 0.32.5.
+#
+# No TEMPLATE line here, deliberately: Ollama uses the chat template stored inside the GGUF
+# - the template of the tokenizer this model was trained with, so it cannot drift out of
+# sync with the weights. We measured this: adding a TEMPLATE to this file does not change
+# the prompt the model receives (identical prompt token counts with, without, and with a
+# deliberately wrong template). With llama.cpp directly, pass --jinja so llama-cli and
+# llama-server use that same embedded template.
+#
 # num_ctx 8192 matches the sequence length this model was fine-tuned at.
 # Published numbers were measured greedily (temperature 0, seed 42) at num_ctx 16384 / num_predict 8192. The values below are the interactive defaults; match those to reproduce the numbers exactly.
-# Standard ChatML. Any Ollama from 0.3 on serves this build.
+# Does not support Ollama's thinking switch - passing `think` to /api/chat returns HTTP 400 (measured). It answers with code directly, which is the point of this build.
 
 FROM ./qwen25_coder_7b-tc.q8_0.gguf
 
-TEMPLATE """{{- if .System }}<|im_start|>system
-{{ .System }}<|im_end|>
-{{ end }}
-{{- range .Messages }}
-{{- if eq .Role "user" }}<|im_start|>user
-{{ .Content }}<|im_end|>
-{{ else if eq .Role "assistant" }}<|im_start|>assistant
-{{ .Content }}<|im_end|>
-{{ end }}
-{{- end }}<|im_start|>assistant
-"""
-
-PARAMETER stop "<|im_end|>"
-PARAMETER stop "<|endoftext|>"
-PARAMETER stop "<|im_start|>"
-
 PARAMETER temperature 0.2
 PARAMETER top_p 0.95
 PARAMETER top_k 20