Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,90 @@
+---
+base_model: microsoft/Phi-4-mini-instruct
+library_name: peft
+license: mit
+pipeline_tag: text-generation
+tags:
+- lora
+- peft
+- small-language-model
+- enterprise-benchmark
+- code-generation
+- base_model:adapter:microsoft/Phi-4-mini-instruct
+---
+
+# phi-4-mini-instruct — Code generation adapter
+
+A LoRA adapter that specialises `microsoft/Phi-4-mini-instruct` (3.80 B parameters) for a single enterprise task: it completes a Python function so that it passes the reference unit tests.
+
+It was produced for the MSc thesis *Fine-Tune or Pay Per Token? An Enterprise Benchmark of Small Language Models* (SRH University Hamburg), which measures fine-tuned small models against frontier provider APIs on accuracy, latency, cost, privacy exposure and return-on-investment breakeven volume. The adapter is released so that the benchmark can be independently verified.
+
+## Measured performance
+
+| Metric | Value |
+|---|---|
+| pass@1 | **0.4287** |
+| Mean latency, batch 1 | 2200 ms |
+| Cost per 1M generated tokens | USD 9.53 |
+
+Measured on a single NVIDIA H200 (141 GB) at batch size one and full utilisation, priced at an imputed USD 3.99 per GPU-hour. Latency excludes network transit. Scores are not comparable across tasks — each task carries its own metric. Evaluation ran on 5 July 2026; the complete matrix is at [`results/benchmark_matrix.csv`](https://github.com/Yusifnuri/slm-benchmark/blob/main/results/benchmark_matrix.csv).
+
+## Training
+
+| | |
+|---|---|
+| Method | LoRA |
+| Dataset | HumanEval (`openai/openai_humaneval`) |
+| Dataset licence | MIT |
+| Training examples | 5,000 (500 held out for checkpoint selection) |
+| Rank / alpha / dropout | 16 / 32 / 0.05 |
+| Target modules | `q_proj`, `k_proj`, `v_proj`, `o_proj` |
+| Learning rate | 2e-4, cosine schedule, 3% warmup |
+| Epochs | 3 |
+| Effective batch size | 16 (4 x 4 gradient accumulation) |
+| Max sequence length | 512 tokens |
+| Optimiser | AdamW |
+| Seed | 42 |
+
+Hyperparameters were held constant across every model and task rather than tuned per cell, so these figures are a conservative lower bound on attainable performance.
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-instruct", device_map="auto")
+model = PeftModel.from_pretrained(base, "<your-hf-username>/phi-4-mini-instruct_code_generation")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-mini-instruct")
+```
+
+The adapter was trained on this prompt format and expects it at inference:
+
+```text
+Complete the following Python function:
+{text}
+```
+
+## Limitations
+
+- Trained once, with a single seed. Reported differences confound model quality with initialisation variance.
+- Specialised to one task on one public corpus. It is not a general-purpose assistant and should not be treated as one.
+- The evaluation corpora are long-standing public benchmarks and are plausibly present in the base model's pretraining data, which inflates absolute scores.
+- Evaluation used 200 held-out instances (all 164 problems for code generation), so detectable effect sizes are bounded at roughly ten percentage points.
+
+## Links
+
+- Code, configurations and evaluation harness: [https://github.com/Yusifnuri/slm-benchmark](https://github.com/Yusifnuri/slm-benchmark)
+- Full benchmark matrix: [`results/benchmark_matrix.csv`](https://github.com/Yusifnuri/slm-benchmark/blob/main/results/benchmark_matrix.csv)
+- Per-request cost analysis: [`results/cost_per_request.csv`](https://github.com/Yusifnuri/slm-benchmark/blob/main/results/cost_per_request.csv)
+
+## Citation
+
+```bibtex
+@mastersthesis{nuri2026finetune,
+  title  = {Fine-Tune or Pay Per Token? An Enterprise Benchmark of Small Language Models},
+  author = {Nuri, Yusif},
+  school = {SRH University Hamburg},
+  year   = {2026}
+}
+```

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9903ef7b3196f831523174e0c509a60269c76384aab5fae36b34c0fcdc55d8be
+size 12591456

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd6878d2c93d9aa166fc56bbe101365748c85775908a4edbb3b7b3616cd2050
+size 15524574

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}