Upload README.md with huggingface_hub

README.md

@@ -35,14 +35,18 @@ stcoder-qwen25-14b is the rule-compliance member of the line: a chat-only fine-t
 
 If you are choosing for the first time, start with [`Mikrodev/stcoder-qwen25-7b-gguf`](https://huggingface.co/Mikrodev/stcoder-qwen25-7b-gguf) at **Q8_0** instead (the fastest per answer of the four (5.8 s), 15/15 delivery, and the highest ChrF among the models that answered every prompt (38.5)). Come to this model for the reasons listed under *Is this the right model for you?*.
 
-> **This model cannot make tool calls.** It is a chat model: you describe a plant requirement, it
-> replies with Structured Text. Tool calling was trained and evaluated across this model line — the
-> Qwen3.5-9B family did learn it (tool-call composite 0.816 at Q8_0, falling to 0.642 at Q4_K_M),
-> while the code-focused families scored 0.02–0.06 and the Gemma family exactly 0.00. Because it was
-> not usable across the line it was **dropped as a product decision**, and these builds are published
-> and supported as chat models. Do not build an agent on them. Those tool-call figures come from a
-> separate internal evaluation that is not part of this release — not from the code study reported below, whose own
-> data and method ship with this model as the detailed report.
+| At a glance | |
+|---|---|
+| Take this build | **Q8_0** — `qwen25_coder_14b-tc.q8_0.gguf`, 14.62 GiB, wants 16.6 GiB free |
+| Dialect-clean replies | **100.0%** against 0.0% for the stock base |
+| Speed | 8.6s per reply, 288 output tokens (median 262) |
+| Runs on | Ollama 0.3+ (tested on 0.32.5), llama.cpp — CPU, GPU or Apple unified memory |
+| Trained for | Mikrodev / ALB Structured Text only — body-only, no POU wrappers, INT milliseconds |
+
+> **Tool calling is not supported on this release.** These are chat models: you describe a plant
+> requirement, they reply with Structured Text. It was trained, measured and then dropped as a
+> product decision — the numbers and the reasoning are under *Not the right tool for*. Do not build
+> an agent on them.
 >
 > **Always compile generated code in ALB / LogicStudio before deployment.** The model produces
 > dialect-correct code, which is not the same as correct control logic.
@@ -74,7 +78,7 @@ slower generation.
 |---|---|---|---|
 | `lora_adapter/` | The LoRA adapter this model was trained as — PEFT adapter on the base model above. Merge it yourself, stack it, or continue training from it. | small | being uploaded |
 | f16 merged weights | f16 is the merged fine-tune at full precision: the reference build, for evaluation or for producing your own quantisations. | ~27.50 GiB | not shipped - rebuild from the adapter (snippet below) |
-| `Modelfile` | One ready-to-run Ollama definition: correct chat template, stop tokens, `num_ctx 8192` (the sequence length this model was trained at) and the system prompt. Its `FROM` points at the Q8_0 file; edit that one line if you downloaded a different quant. | small | in this repo |
+| `Modelfile` | One ready-to-run Ollama definition: the system prompt, the sampling defaults and `num_ctx 8192` (the sequence length this model was trained at). It deliberately carries **no chat template** — Ollama uses the chat template stored inside the GGUF, so the chat format is the trained one and cannot drift out of sync with this file. Its `FROM` points at the Q8_0 file; edit that one line if you downloaded a different quant. | small | in this repo |
 | `article_stcoder-qwen25-14b.html`, `article_stcoder-qwen25-14b.docx` | The full evaluation report for this model. | |
 
 ## Quick start with Ollama
@@ -122,8 +126,37 @@ You get a body-only `iecst` block: `VAR` declarations plus logic, millisecond `I
 positional function-block calls, no `PROGRAM` wrapper. Paste it into ALB / LogicStudio and compile.
 
 For a different build, download that GGUF instead and change the Modelfile's `FROM` line to its
-filename (the Modelfile lists the alternatives at the top). With llama.cpp instead of Ollama, point `llama-cli -m <file>.gguf` at the
-GGUF and pass the same system prompt.
+filename (the Modelfile lists the alternatives at the top).
+
+With llama.cpp instead of Ollama, run `llama-cli -m <file>.gguf --jinja` and pass the same system
+prompt. **`--jinja` matters:** it makes llama.cpp use the chat template stored inside the GGUF — the
+one this model was trained with — instead of guessing a format.
+
+## What the fine-tune actually changes
+
+One prompt from the study below, sent to the stock base and to this fine-tune under the same short
+system prompt that lists **no** dialect rules:
+
+> *We've got a conveyor with a pre-start warning horn. When the operator hits the start button I need the horn to sound for 5 seconds first, then the motor kicks in and the horn goes quiet.*
+
+The stock base answered with named function-block parameters, a TIME literal and a PROGRAM wrapper — constructs the Mikrodev runtime rejects:
+
+```iecst
+Timer5Sec(IN := FALSE, PT := T#5s);
+```
+
+This fine-tune, same prompt, no rules in the prompt:
+
+```iecst
+HORN_MS : INT := 5000;                        (* in VAR CONSTANT *)
+tHorn(bStartBtn AND NOT bFault AND NOT bStopBtn, HORN_MS);
+```
+
+Positional function-block call, delay as an `INT` in milliseconds, no wrapper — the dialect came out
+of the weights, not out of the prompt. Both snippets are verbatim from the recorded run.
+
+> These lines show **dialect**, not correctness. R24 certifies that no forbidden construct appears;
+> it does not check that the logic works. Read *Weaknesses* before you trust an answer.
 
 ## Use the LoRA adapter directly
 
@@ -251,6 +284,10 @@ and limitations — ships in this repo:
 - Readers who want the line default. That is stcoder-qwen25-7b at Q6_K: faster per answer, smaller, and higher ChrF at full delivery. Come to the 14B for the clean rate, not as a general upgrade.
 - Any dialect other than Mikrodev LogicStudio. It was trained to violate conventions that other IEC 61131-3 environments require, so its output is deliberately wrong for them: no POU wrappers, no TIME literals, no named parameters, no output arrows.
 
+Those tool-call figures come from a separate internal evaluation that is not part of this release —
+not from the code study reported above, whose own data and method ship with this model as the
+detailed report.
+
 ## Limitations of the evaluation
 
 - **Quantisation was not matched.** This fine-tune ran at Q6_K; the stock base ran at the
@@ -271,10 +308,22 @@ and limitations — ships in this repo:
 
 A curated in-house multi-task PLC corpus (approximately 2,930 training and 550 validation examples)
 focused on Structured Text generation, written against the ALB / Mikrodev LogicStudio rule set. The
-dataset is not publicly released. Sequence length 8192 tokens.
+dataset is not publicly released.
 
 Prompts are mostly English with a Turkish minority (10.8% of training prompts contain Turkish). Code, identifiers and code comments are always English; the model's conversational prose follows the language you write in.
 
+| Training setting | Value |
+|---|---|
+| Method | LoRA (PEFT) supervised fine-tune |
+| LoRA rank / alpha | 32 / 32 (dropout 0.0) |
+| Epochs | 2 |
+| Learning rate | 0.0001 |
+| Sequence length | 8192 tokens |
+| Effective batch | 8 (batch 1 x grad-accum 8) |
+
+The published LoRA adapter is exactly this run's output, so anything above can be reproduced or
+continued from it.
+
 ## Licence and attribution
 
 apache-2.0. Fine-tuned from [`Qwen/Qwen2.5-Coder-14B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct); the base