Text Generation
Transformers
Safetensors
code
ivme_coder
language-model
transformer
rope
swiglu
muon
from-scratch
tiny
small
decoder-only
python
custom_code
Instructions to use IvmeLabs/Ivme-Coder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IvmeLabs/Ivme-Coder-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IvmeLabs/Ivme-Coder-v1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("IvmeLabs/Ivme-Coder-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IvmeLabs/Ivme-Coder-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IvmeLabs/Ivme-Coder-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IvmeLabs/Ivme-Coder-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IvmeLabs/Ivme-Coder-v1
- SGLang
How to use IvmeLabs/Ivme-Coder-v1 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 "IvmeLabs/Ivme-Coder-v1" \ --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": "IvmeLabs/Ivme-Coder-v1", "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 "IvmeLabs/Ivme-Coder-v1" \ --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": "IvmeLabs/Ivme-Coder-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IvmeLabs/Ivme-Coder-v1 with Docker Model Runner:
docker model run hf.co/IvmeLabs/Ivme-Coder-v1
Update README.md
Browse files
README.md
CHANGED
|
@@ -49,6 +49,14 @@ library_name: transformers
|
|
| 49 |
|
| 50 |
Coder's architecture deliberately mirrors the same core recipe as the Conversate line — RoPE, SwiGLU, RMSNorm, tied embeddings, Muon-optimized body weights. The point of keeping the recipe constant across both lines is to isolate what changes with domain-specific data and a narrower target distribution, not to introduce a second set of untested architectural choices at the same time.
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
---
|
| 53 |
|
| 54 |
## Training
|
|
|
|
| 49 |
|
| 50 |
Coder's architecture deliberately mirrors the same core recipe as the Conversate line — RoPE, SwiGLU, RMSNorm, tied embeddings, Muon-optimized body weights. The point of keeping the recipe constant across both lines is to isolate what changes with domain-specific data and a narrower target distribution, not to introduce a second set of untested architectural choices at the same time.
|
| 51 |
|
| 52 |
+
<a href="https://hfviewer.com/IvmeLabs/Ivme-Coder-v1?utm_source=huggingface&utm_medium=embedded_model_card&utm_campaign=IvmeLabs__Ivme-Coder-v1_card&utm_content=embedded_card_open_viewer&from=embedded-model-card" target="_blank" rel="noopener">
|
| 53 |
+
<img
|
| 54 |
+
src="https://hfviewer.com/api/card.svg?source=IvmeLabs%2FIvme-Coder-v1&granularity=auto&v=20260516-title-pills-card"
|
| 55 |
+
alt="Architecture graph for IvmeLabs/Ivme-Coder-v1. Open in hfviewer"
|
| 56 |
+
width="100%"
|
| 57 |
+
/>
|
| 58 |
+
</a>
|
| 59 |
+
|
| 60 |
---
|
| 61 |
|
| 62 |
## Training
|