Instructions to use Bayhakl1/MiniGrimm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bayhakl1/MiniGrimm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Bayhakl1/MiniGrimm")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Bayhakl1/MiniGrimm") model = AutoModelForCausalLM.from_pretrained("Bayhakl1/MiniGrimm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Bayhakl1/MiniGrimm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Bayhakl1/MiniGrimm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bayhakl1/MiniGrimm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Bayhakl1/MiniGrimm
- SGLang
How to use Bayhakl1/MiniGrimm 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/MiniGrimm" \ --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/MiniGrimm", "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/MiniGrimm" \ --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/MiniGrimm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Bayhakl1/MiniGrimm with Docker Model Runner:
docker model run hf.co/Bayhakl1/MiniGrimm
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,21 @@ Evaluated after SFT on **ArithMark 3.0** (arithmetic reasoning):
|
|
| 50 |
*(Not bad for a 42M non-embedding model, though it will still make plenty of mistakes on multi-step word problems or larger numbers.)*
|
| 51 |
|
| 52 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
|
|
|
| 54 |
## Architecture & Training Summary
|
| 55 |
|
| 56 |
Instead of a wide, shallow network, MiniGrimm uses a tall, narrow layout (28 layers at `d_model=384`) paired with modern stability tweaks:
|
|
|
|
| 50 |
*(Not bad for a 42M non-embedding model, though it will still make plenty of mistakes on multi-step word problems or larger numbers.)*
|
| 51 |
|
| 52 |
---
|
| 53 |
+
Other Benchmarks:
|
| 54 |
+
|
| 55 |
+
| Benchmark | Accuracy (Raw) | Accuracy (Norm) | Notes |
|
| 56 |
+
| :--- | :---: | :---: | :--- |
|
| 57 |
+
| **SciQ** | 70.7% (±1.44) | 63.0% (±1.53) | Science QA |
|
| 58 |
+
| **PIQA** | 61.7% (±1.13) | 62.0% (±1.13) | Physical commonsense |
|
| 59 |
+
| **Winogrande** | 52.4% (±1.40) | — | Pronoun resolution |
|
| 60 |
+
| **BoolQ** | 48.6% (±0.87) | — | Yes/No reading comprehension |
|
| 61 |
+
| **ARC-Easy** | 48.6% (±1.03) | 43.8% (±1.02) | Grade-school science |
|
| 62 |
+
| **HellaSwag** | 29.1% (±0.45) | 31.7% (±0.46) | Sentence completion |
|
| 63 |
+
| **OpenBookQA** | 19.2% (±1.76) | 30.0% (±2.05) | Elementary science facts |
|
| 64 |
+
| **ARC-Challenge** | 22.3% (±1.22) | 27.2% (±1.30) | Harder science reasoning |
|
| 65 |
+
| **LAMBADA (OpenAI)** | 26.9% (±0.62) | — | Perplexity: 83.15 (±3.71) |
|
| 66 |
|
| 67 |
+
---
|
| 68 |
## Architecture & Training Summary
|
| 69 |
|
| 70 |
Instead of a wide, shallow network, MiniGrimm uses a tall, narrow layout (28 layers at `d_model=384`) paired with modern stability tweaks:
|