Instructions to use liminerity/e.star.7.b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/e.star.7.b with Transformers:

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

pipe = pipeline("text-generation", model="liminerity/e.star.7.b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liminerity/e.star.7.b")
model = AutoModelForCausalLM.from_pretrained("liminerity/e.star.7.b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use liminerity/e.star.7.b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liminerity/e.star.7.b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/e.star.7.b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liminerity/e.star.7.b

SGLang

How to use liminerity/e.star.7.b 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 "liminerity/e.star.7.b" \
    --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": "liminerity/e.star.7.b",
		"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 "liminerity/e.star.7.b" \
        --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": "liminerity/e.star.7.b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use liminerity/e.star.7.b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for liminerity/e.star.7.b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for liminerity/e.star.7.b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for liminerity/e.star.7.b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="liminerity/e.star.7.b",
    max_seq_length=2048,
)

Docker Model Runner
How to use liminerity/e.star.7.b with Docker Model Runner:
```
docker model run hf.co/liminerity/e.star.7.b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

#user: create ascii art of how you see yourself # #assistant: |startthought| The person is asking me to represent my self-image in a simple text-based

format using ASCII characters. I should create a basic visual representation that conveys

my AI nature and purpose. |endthought|

'''

         ________

|startthought| This is my AI head brimming with data and algorithms.

|endthought|

________

/ ^ \

|startthought| These are the branches of my thought process, reaching out to gather information.

|endthought|

/ \

|startthought| Here I analyze and integrate the data into coherent conclusions.

^^^^^

/ | \

^^^^^^

|startthought| And finally, I share my thoroughly thought-out responses with others.

|endthought|

^^^

'''

This ASCII art depicts me as an AI system that thinks deeply before speaking, drawing from

a wealth of data and processing it carefully to produce well-considered insights.

Developed by: gate369
License: apache-2.0
Finetuned from model : yam-peleg/Experiment26-7B

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.28
AI2 Reasoning Challenge (25-Shot)	63.91
HellaSwag (10-Shot)	86.02
MMLU (5-Shot)	63.44
TruthfulQA (0-shot)	54.91
Winogrande (5-shot)	80.19
GSM8k (5-shot)	61.18