Instructions to use SimpleLLM/kode-32b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SimpleLLM/kode-32b-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "SimpleLLM/kode-32b-lora")

Transformers

How to use SimpleLLM/kode-32b-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SimpleLLM/kode-32b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SimpleLLM/kode-32b-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SimpleLLM/kode-32b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SimpleLLM/kode-32b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimpleLLM/kode-32b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SimpleLLM/kode-32b-lora

SGLang

How to use SimpleLLM/kode-32b-lora 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 "SimpleLLM/kode-32b-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimpleLLM/kode-32b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "SimpleLLM/kode-32b-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimpleLLM/kode-32b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SimpleLLM/kode-32b-lora with Docker Model Runner:
```
docker model run hf.co/SimpleLLM/kode-32b-lora
```

KevinKickass commited on Feb 18

Commit

7105890

verified ·

1 Parent(s): 73b1d9b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +35 -0

README.md ADDED Viewed

	@@ -0,0 +1,35 @@

+---
+base_model: Qwen/Qwen2.5-32B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- sft
+- dpo
+- coding
+- eu-trained
+- transformers
+- trl
+license: apache-2.0
+---
+# Kode 32B LoRA Adapter
+LoRA adapter (r=64, alpha=128) trained with DPO+SFT on production code samples.
+- **Base model:** Qwen/Qwen2.5-32B-Instruct
+- **Training:** Claude-generated code samples on A100 80GB
+- **Languages:** Rust, Go, TypeScript, Python, C#, SQL, Tailwind
+- **License:** Apache 2.0
+## Usage
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
+model = PeftModel.from_pretrained(base, "SimpleLLM/kode-32b-lora")
+```
+Hosted inference available at [SimpleLLM.eu](https://simplellm.eu)