Instructions to use OddTheGreat/lastman_12B_V.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/lastman_12B_V.1 with Transformers:

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

pipe = pipeline("text-generation", model="OddTheGreat/lastman_12B_V.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/lastman_12B_V.1")
model = AutoModelForCausalLM.from_pretrained("OddTheGreat/lastman_12B_V.1", device_map="auto")
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 Settings

vLLM

How to use OddTheGreat/lastman_12B_V.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OddTheGreat/lastman_12B_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/lastman_12B_V.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OddTheGreat/lastman_12B_V.1

SGLang

How to use OddTheGreat/lastman_12B_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/lastman_12B_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/lastman_12B_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/lastman_12B_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/lastman_12B_V.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OddTheGreat/lastman_12B_V.1 with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/lastman_12B_V.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a merge of pre-trained language models

Goal of this merge was to enhance roleplay capabilities and overall performance of Nomad_12b

I tested this model over a week, in rp, but also for work and as creative assistant, and results were good. Model is very attentive to char card, and to context in general, smart, creative enough, it follows instructions just fine. Model is surprisingly stable, on 16k context it not loosing dramatically in quality, and even if used on completely wrong settings it will not break.

Of course, it is not censored (like all mistral models), and fine for ERP.

Ru performance is good enough to use it as assistant or chat, for rp En is better.

Tested on mistral v7 template t 1.04.