Instructions to use OddTheGreat/Core_24B_V.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/Core_24B_V.1 with Transformers:

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

pipe = pipeline("text-generation", model="OddTheGreat/Core_24B_V.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/Core_24B_V.1")
model = AutoModelForCausalLM.from_pretrained("OddTheGreat/Core_24B_V.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OddTheGreat/Core_24B_V.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OddTheGreat/Core_24B_V.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OddTheGreat/Core_24B_V.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OddTheGreat/Core_24B_V.1

SGLang

How to use OddTheGreat/Core_24B_V.1 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 "OddTheGreat/Core_24B_V.1" \
    --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": "OddTheGreat/Core_24B_V.1",
		"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 "OddTheGreat/Core_24B_V.1" \
        --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": "OddTheGreat/Core_24B_V.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OddTheGreat/Core_24B_V.1 with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/Core_24B_V.1
```

My feedback.

by rengecky - opened Apr 19, 2025

Discussion

rengecky

Apr 19, 2025

After using the model for three weeks, I can say it’s my favorite. Apparatus is good, but this model is better. It's smarter, has a better understanding of context, and follows instructions more accurately. Even though I searched, I couldn’t find a model that understands me better, and I’ve tried a lot over the past couple of years.
In Russian, it still understands context, but the grammar is poor, and it often repeats itself and hallucinates (just like other models).

My settings: T 1.01 Min P 0.035 Penalty 0.05 Smoothing Factor 0.3 DRY [1 2 4] – everything else off
Template: Mistral V7

OddTheGreat

Owner Apr 20, 2025

Thank you for feedback! Glad that you liked model! For Russian performance, i use ChatML, other settings on screenshot, maybe on these settings will work better. Also, if you use not fully ru cards, performance is significantly worse.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment