Instructions to use OddTheGreat/Unity-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/Unity-12B with Transformers:

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

pipe = pipeline("text-generation", model="OddTheGreat/Unity-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/Unity-12B")
model = AutoModelForCausalLM.from_pretrained("OddTheGreat/Unity-12B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OddTheGreat/Unity-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OddTheGreat/Unity-12B"
# 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/Unity-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OddTheGreat/Unity-12B

SGLang

How to use OddTheGreat/Unity-12B 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/Unity-12B" \
    --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/Unity-12B",
		"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/Unity-12B" \
        --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/Unity-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OddTheGreat/Unity-12B with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/Unity-12B
```

OddTheGreat commited on Jan 26, 2025

Commit

951ab11

verified ·

1 Parent(s): 6e70bac

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -38

README.md CHANGED Viewed

@@ -1,46 +1,18 @@
 ---
 base_model:
-- OddTheGreat/PartTwo-12B
 - OddTheGreat/PartOne-12B
 library_name: transformers
 tags:
-- mergekit
 - merge
 ---
-# merge
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [OddTheGreat/PartOne-12B](https://huggingface.co/OddTheGreat/PartOne-12B) as a base.
-### Models Merged
-The following models were included in the merge:
-* [OddTheGreat/PartTwo-12B](https://huggingface.co/OddTheGreat/PartTwo-12B)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: OddTheGreat/PartOne-12B
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: OddTheGreat/PartTwo-12B
-    parameters:
-      density: 0.5
-      weight: 0.5
-merge_method: ties
-base_model: OddTheGreat/PartOne-12B
-parameters:
-  normalize: false
-  int8_mask: true
-dtype: float16
-```

 ---
 base_model:
 - OddTheGreat/PartOne-12B
+- OddTheGreat/PartTwo-12B
 library_name: transformers
 tags:
 - merge
+- Roleplay
+- Creative
+language:
+- ru
+- en
 ---
+This is a merge of pre-trained language models
+Main usage - RP, ERP, Chat-asisstant on russian and english languages
+This model is created to work in SillyTavern
+Best use ChatML format, works really good. Tested on Temerature 1.01