Instructions to use jeonsworld/CarbonVillain-en-10.7B-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeonsworld/CarbonVillain-en-10.7B-v4 with Transformers:

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

pipe = pipeline("text-generation", model="jeonsworld/CarbonVillain-en-10.7B-v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jeonsworld/CarbonVillain-en-10.7B-v4")
model = AutoModelForCausalLM.from_pretrained("jeonsworld/CarbonVillain-en-10.7B-v4")
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 jeonsworld/CarbonVillain-en-10.7B-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeonsworld/CarbonVillain-en-10.7B-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeonsworld/CarbonVillain-en-10.7B-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jeonsworld/CarbonVillain-en-10.7B-v4

SGLang

How to use jeonsworld/CarbonVillain-en-10.7B-v4 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 "jeonsworld/CarbonVillain-en-10.7B-v4" \
    --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": "jeonsworld/CarbonVillain-en-10.7B-v4",
		"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 "jeonsworld/CarbonVillain-en-10.7B-v4" \
        --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": "jeonsworld/CarbonVillain-en-10.7B-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jeonsworld/CarbonVillain-en-10.7B-v4 with Docker Model Runner:
```
docker model run hf.co/jeonsworld/CarbonVillain-en-10.7B-v4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CarbonVillain

This is a model created without learning to oppose indiscriminate carbon emissions.

This model is an experimental version created using mergekit.

merge models
- jeonsworld/CarbonVillain-en-10.7B-v1
- jeonsworld/CarbonVillain-en-10.7B-v2
method: slerp

Ranked 1st 2023.12.30

thanks to KyujinHan, Yağız Çalık and VAGO solutions

Prompt Template(s)

### User:
{user}

### Assistant:
{asistant}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.52
AI2 Reasoning Challenge (25-Shot)	71.25
HellaSwag (10-Shot)	88.48
MMLU (5-Shot)	66.27
TruthfulQA (0-shot)	71.95
Winogrande (5-shot)	83.58
GSM8k (5-shot)	65.58

Downloads last month: 13,758

Safetensors

Model size

11B params

Tensor type

F16

Model tree for jeonsworld/CarbonVillain-en-10.7B-v4

Merges

1 model

Quantizations

5 models

Spaces using jeonsworld/CarbonVillain-en-10.7B-v4 2

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

71.250
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.480
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

66.270
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

71.950
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.580
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

65.580