Instructions to use OddTheGreat/Lastman_12B_V.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/Lastman_12B_V.2 with Transformers:

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

pipe = pipeline("text-generation", model="OddTheGreat/Lastman_12B_V.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/Lastman_12B_V.2")
model = AutoModelForCausalLM.from_pretrained("OddTheGreat/Lastman_12B_V.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OddTheGreat/Lastman_12B_V.2 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.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OddTheGreat/Lastman_12B_V.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OddTheGreat/Lastman_12B_V.2

SGLang

How to use OddTheGreat/Lastman_12B_V.2 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.2" \
    --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": "OddTheGreat/Lastman_12B_V.2",
		"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 "OddTheGreat/Lastman_12B_V.2" \
        --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": "OddTheGreat/Lastman_12B_V.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OddTheGreat/Lastman_12B_V.2 with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/Lastman_12B_V.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Lastman_12B_V.2

This is a merge of pre-trained language models

Goal of this merge was to create good all-round model for creative writing, casual chat and roleplay, for fast everyday use on limited vram.

Model is creative enough, good at instruction following, and has acceptable context sensitivity for 12b mistral. Narration is nice. If user is described in char card, model could reply for you.

Ru was tested too, on q4 is bad, on q5 and higher is good, not too dry, not too dumb.

Use Mistral tepmlate, t1.04.