Quickstart prints the project field only (priority is unreliable)

MODEL_CARD.ko.md

@@ -46,6 +46,8 @@ tok = AutoTokenizer.from_pretrained(BASE)
 model = AutoModelForCausalLM.from_pretrained(BASE, dtype=torch.bfloat16, device_map="auto")
 model = PeftModel.from_pretrained(model, "ThakiCloud/FleetWorker-E4B", subfolder="adapter").eval()
 
+import json
+
 SYSTEM = "You triage a task-board item. Output exactly one compact JSON object with keys \"project\" and \"priority\" and nothing else. \"project\" is one of: <the project labels the model was trained on, comma separated>, or \"other\"; \"unknown\" if the text gives no way to tell. \"priority\" is one of: P0, P1, P2, P3."
 USER = "title: Add retry with backoff to the nightly export job"
 messages = [
@@ -55,7 +57,8 @@ messages = [
 inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False,
                                return_tensors="pt", return_dict=True).to(model.device)
 out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
-print(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+pred = json.loads(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+print(pred["project"])  # project only: the priority field is unreliable, see Limitations
 ```
 
 ### Merged BF16
@@ -69,6 +72,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 tok = AutoTokenizer.from_pretrained("ThakiCloud/FleetWorker-E4B")
 model = AutoModelForCausalLM.from_pretrained("ThakiCloud/FleetWorker-E4B", dtype=torch.bfloat16, device_map="auto").eval()
 
+import json
+
 SYSTEM = "You triage a task-board item. Output exactly one compact JSON object with keys \"project\" and \"priority\" and nothing else. \"project\" is one of: <the project labels the model was trained on, comma separated>, or \"other\"; \"unknown\" if the text gives no way to tell. \"priority\" is one of: P0, P1, P2, P3."
 USER = "title: Add retry with backoff to the nightly export job"
 messages = [
@@ -78,7 +83,8 @@ messages = [
 inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False,
                                return_tensors="pt", return_dict=True).to(model.device)
 out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
-print(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+pred = json.loads(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+print(pred["project"])  # project only: the priority field is unreliable, see Limitations
 ```
 
 ### llama.cpp (GGUF)

README.md

@@ -54,7 +54,7 @@ title: Add retry with backoff to the nightly export job<turn|>
 
 Output format: one compact JSON object: `{"project":<label from the prompt list, "other" or "unknown">,"priority":"P0"|"P1"|"P2"|"P3"}`.
 
-Replace the angle-bracket project list with the label set you fine-tune for. Show the suggested priority to a person; do not write it back automatically.
+Replace the angle-bracket project list with the label set you fine-tune for. The example prints the project only: the model still emits a priority field, but it answers P0 for 120 of 151 items whose priority was never set, so do not display it as urgency and do not write it back to the board. If you want a priority hint, show it to a person on explicitly prioritised items only.
 
 ### Transformers + PEFT adapter
 
@@ -68,6 +68,8 @@ tok = AutoTokenizer.from_pretrained(BASE)
 model = AutoModelForCausalLM.from_pretrained(BASE, dtype=torch.bfloat16, device_map="auto")
 model = PeftModel.from_pretrained(model, "ThakiCloud/FleetWorker-E4B", subfolder="adapter").eval()
 
+import json
+
 SYSTEM = "You triage a task-board item. Output exactly one compact JSON object with keys \"project\" and \"priority\" and nothing else. \"project\" is one of: <the project labels the model was trained on, comma separated>, or \"other\"; \"unknown\" if the text gives no way to tell. \"priority\" is one of: P0, P1, P2, P3."
 USER = "title: Add retry with backoff to the nightly export job"
 messages = [
@@ -77,7 +79,8 @@ messages = [
 inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False,
                                return_tensors="pt", return_dict=True).to(model.device)
 out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
-print(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+pred = json.loads(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+print(pred["project"])  # project only: the priority field is unreliable, see Limitations
 ```
 
 ### Merged BF16
@@ -91,6 +94,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 tok = AutoTokenizer.from_pretrained("ThakiCloud/FleetWorker-E4B")
 model = AutoModelForCausalLM.from_pretrained("ThakiCloud/FleetWorker-E4B", dtype=torch.bfloat16, device_map="auto").eval()
 
+import json
+
 SYSTEM = "You triage a task-board item. Output exactly one compact JSON object with keys \"project\" and \"priority\" and nothing else. \"project\" is one of: <the project labels the model was trained on, comma separated>, or \"other\"; \"unknown\" if the text gives no way to tell. \"priority\" is one of: P0, P1, P2, P3."
 USER = "title: Add retry with backoff to the nightly export job"
 messages = [
@@ -100,7 +105,8 @@ messages = [
 inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False,
                                return_tensors="pt", return_dict=True).to(model.device)
 out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
-print(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+pred = json.loads(tok.decode(out[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+print(pred["project"])  # project only: the priority field is unreliable, see Limitations
 ```
 
 ### llama.cpp (GGUF)