Instructions to use inflatebot/L3-8B-Helium3-baseLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inflatebot/L3-8B-Helium3-baseLlama with Transformers:

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

pipe = pipeline("text-generation", model="inflatebot/L3-8B-Helium3-baseLlama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inflatebot/L3-8B-Helium3-baseLlama")
model = AutoModelForCausalLM.from_pretrained("inflatebot/L3-8B-Helium3-baseLlama")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inflatebot/L3-8B-Helium3-baseLlama with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inflatebot/L3-8B-Helium3-baseLlama"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inflatebot/L3-8B-Helium3-baseLlama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/inflatebot/L3-8B-Helium3-baseLlama

SGLang

How to use inflatebot/L3-8B-Helium3-baseLlama 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 "inflatebot/L3-8B-Helium3-baseLlama" \
    --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": "inflatebot/L3-8B-Helium3-baseLlama",
		"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 "inflatebot/L3-8B-Helium3-baseLlama" \
        --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": "inflatebot/L3-8B-Helium3-baseLlama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use inflatebot/L3-8B-Helium3-baseLlama with Docker Model Runner:
```
docker model run hf.co/inflatebot/L3-8B-Helium3-baseLlama
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

helium-3-r2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Helium3, but the base model is Llama-3. Ended up being too dry, but if He3's too horny for you, try this one.

GGUFs by mradermacher

Merge Method

This model was merged using the Model Stock merge method using NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: inflatebot/helide-beta-r4
  - model: inflatebot/helide-beta-r1
  - model: inflatebot/helide-beta-r0

merge_method: model_stock
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16