Text Generation
Transformers
Safetensors
code
English
llama
python
code-completion
fill-in-the-middle
fim
text-generation-inference
Instructions to use Bayhakl1/GrimmCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bayhakl1/GrimmCoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Bayhakl1/GrimmCoder")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Bayhakl1/GrimmCoder") model = AutoModelForCausalLM.from_pretrained("Bayhakl1/GrimmCoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Bayhakl1/GrimmCoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Bayhakl1/GrimmCoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bayhakl1/GrimmCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Bayhakl1/GrimmCoder
- SGLang
How to use Bayhakl1/GrimmCoder with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Bayhakl1/GrimmCoder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bayhakl1/GrimmCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Bayhakl1/GrimmCoder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bayhakl1/GrimmCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Bayhakl1/GrimmCoder with Docker Model Runner:
docker model run hf.co/Bayhakl1/GrimmCoder
|
Download README.md from Bayhakl1/GrimmCoder: direct link, hf CLI and curl.
- Browser
- Download file 4.86 kB
-
https://huggingface.co/Bayhakl1/GrimmCoder/resolve/main/README.md
- Command line
-
hf download hf://Bayhakl1/GrimmCoder/README.md
-
curl -L -o README.md https://huggingface.co/Bayhakl1/GrimmCoder/resolve/main/README.md
4.86 kB
metadata
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 | |
| 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 | >` |
| `< | fim_prefix | >` |
| `< | fim_middle | >` |
| `< | fim_suffix | >` |
| `< | pad | >` |
Usage (transformers)
1. Left-to-Right Code Completion
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:
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 (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"""\noften resemble empty stub/interface files (predicting<|endoftext|>or starting anotherdef). 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/48passes infloat32whilebfloat16scores9/164/5.49%greedy). Also keeprepetition_penalty=1.0when usingtransformersgenerate(), as HF appliesrepetition_penaltyacross 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.