--- language: - code - en license: apache-2.0 datasets: - bigcode/starcoderdata library_name: transformers pipeline_tag: text-generation tags: - code - python - code-completion - fill-in-the-middle - fim - llama --- # GrimmCoder **GrimmCoder** is a ~107M-parameter LLaMA-style decoder-only transformer trained from scratch exclusively on Python source code for both **left-to-right completion** and **Fill-in-the-Middle (FIM)** code completion. ## Model Summary | Property | Value | |---|---| | Architecture | LLaMA (`LlamaForCausalLM`, pre-norm, RoPE, SwiGLU, GQA, tied embeddings) | | Parameters | ~106.98M total (~100.69M non-embedding) | | Context Length | 2048 tokens | | Hidden Size (`d_model`) | 768 | | Layers | 16 | | Attention Heads | 12 query heads / 4 KV heads (GQA) | | FFN Intermediate Size | 2048 (SwiGLU) | | Vocabulary | 8192 (byte-level BPE trained on Python) | | Training Data | `bigcode/starcoderdata` (Python subset) | | Tokens / Checkpoint | 7.93B tokens (step 61,500, validation loss 1.2321) | ## Special Tokens | Token | ID | Purpose | |---|---|---| | `<|endoftext|>` | `0` | BOS / EOS / document delimiter | | `<|fim_prefix|>` | `1` | FIM prefix marker | | `<|fim_middle|>` | `2` | FIM middle marker (model generates from here) | | `<|fim_suffix|>` | `3` | FIM suffix marker | | `<|pad|>` | `4` | Padding token | ## Usage (`transformers`) ### 1. Left-to-Right Code Completion ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Bayhakl1/GrimmCoder" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, dtype=torch.bfloat16, device_map="auto", ) prompt = """def binary_search(arr, target): lo, hi = 0, len(arr) - 1 """ inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device) outputs = model.generate( **inputs, max_new_tokens=128, do_sample=True, temperature=0.2, top_p=0.95, eos_token_id=[0, 1, 2, 3, 4], pad_token_id=4, ) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ### 2. Fill-in-the-Middle (FIM) The model was trained 50/50 on PSM and SPM Fill-in-the-Middle formatting. Note `add_special_tokens=False` when tokenizing raw prefix/suffix segments: ```python prefix = "def add(a: int, b: int) -> int:\n " suffix = "\n\nprint(add(2, 3))\n" # PSM format: <|fim_prefix|> prefix <|fim_suffix|> suffix <|fim_middle|> fim_prompt = f"<|fim_prefix|>{prefix}<|fim_suffix|>{suffix}<|fim_middle|>" inputs = tokenizer(fim_prompt, return_tensors="pt", add_special_tokens=False).to(model.device) outputs = model.generate( **inputs, max_new_tokens=64, do_sample=True, temperature=0.2, top_p=0.95, eos_token_id=[0, 1, 2, 3, 4], pad_token_id=4, ) middle_ids = outputs[0][inputs["input_ids"].shape[1]:] middle = tokenizer.decode(middle_ids, skip_special_tokens=True) print(prefix + middle + suffix) ``` ## Evaluation (HumanEval) Evaluated on [`openai/openai_humaneval`](https://huggingface.co/datasets/openai/openai_humaneval) (164 Python problems) using `transformers` (`bfloat16`): | Prompt Mode | Decoding | `pass@1` | Solved | |---|---|---|---| | Left-to-Right (`prompt.rstrip("\n")`, ending on `"""`) | greedy (`do_sample=False`, `max_new_tokens=128`) | **5.49%** | 9 / 164 | | Left-to-Right (`prompt.rstrip("\n")`, ending on `"""`) | `temperature=0.2`, `top_k=50`, `top_p=0.95`, `repetition_penalty=1.1` | **4.88%** | 8 / 164 | | Fill-in-the-Middle (PSM: `<\|fim_prefix\|>{prompt}<\|fim_suffix\|>\n<\|fim_middle\|>`) | greedy (`do_sample=False`, `max_new_tokens=384`) | **4.27%** | 7 / 164 | | Left-to-Right (raw `prompt` ending on `"""\n`) | greedy (`do_sample=False`, `max_new_tokens=384`) | **0.00%** | 0 / 164 | > **Notes:** > - As a base completion model pretrained on raw `starcoderdata`, prompts ending directly on `"""\n` often resemble empty stub/interface files (predicting `<|endoftext|>` or starting another `def`). Stripping the trailing newline so the prompt ends on `"""` (or prompting in FIM-PSM mode) cues the model to emit the indented function body instead. > - In `bfloat16` (`transformers`), minor intermediate precision rounding can affect borderline tokens (for example, `HumanEval/48` passes in `float32` while `bfloat16` scores `9/164` / `5.49%` greedy). Also keep `repetition_penalty=1.0` when using `transformers` `generate()`, as HF applies `repetition_penalty` across the prompt docstring as well. ## Limitations - Trained exclusively on Python source code; not intended as a general natural-language chat or instruction-following model. - Base / completion model: responds best to code prompts and FIM markers rather than conversational Q&A.