Instructions to use SebastianSchramm/Cerebras-GPT-111M-instruction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SebastianSchramm/Cerebras-GPT-111M-instruction with Transformers:

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

pipe = pipeline("text-generation", model="SebastianSchramm/Cerebras-GPT-111M-instruction")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SebastianSchramm/Cerebras-GPT-111M-instruction")
model = AutoModelForCausalLM.from_pretrained("SebastianSchramm/Cerebras-GPT-111M-instruction")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SebastianSchramm/Cerebras-GPT-111M-instruction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SebastianSchramm/Cerebras-GPT-111M-instruction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SebastianSchramm/Cerebras-GPT-111M-instruction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SebastianSchramm/Cerebras-GPT-111M-instruction

SGLang

How to use SebastianSchramm/Cerebras-GPT-111M-instruction 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 "SebastianSchramm/Cerebras-GPT-111M-instruction" \
    --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": "SebastianSchramm/Cerebras-GPT-111M-instruction",
		"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 "SebastianSchramm/Cerebras-GPT-111M-instruction" \
        --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": "SebastianSchramm/Cerebras-GPT-111M-instruction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SebastianSchramm/Cerebras-GPT-111M-instruction with Docker Model Runner:
```
docker model run hf.co/SebastianSchramm/Cerebras-GPT-111M-instruction
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Instruction-tuned Cerebras GPT 111M

The smallest of cerebras GPT models with only 111M parameters instruction fine-tuned.

Model Description

Instruction fine-tuned cerebras-GPT-111M

Evaluation

The model has been evaluated with Huggingface's Open LLM leaderboard. Have a look at the leaderboard for more details: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard The performance of the instruction fine-tuned model does improve compared to the cerebras base model by about 5.7% (average score):

Model	Average	ARC (25-shot)	HellaSwag (10-shot)	MMLU (5-shot)	TruthfulQA (0-shot)
SebastianSchramm/Cerebras-GPT-111M-instruction	31.6	24.3	26.2	26.5	49.5
cerebras/Cerebras-GPT-111M	29.9	20	26.7	26.7	46.3

Training data

The model was fine-tuned with the following data: alpaca_gpt4_data (data generated by GPT-4 using Alpaca prompts for fine-tuning LLMs) and alpaca_data_cleaned.

Prompt template

Fine-tuning was performed with the promp template from stanford alpaca:

PROMPT_DICT = {
    "prompt_input": (
        "Below is an instruction that describes a task, paired with an input that provides further context. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
    ),
    "prompt_no_input": (
        "Below is an instruction that describes a task. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Response:"
    ),
}

Usage

It is recommended to format input according to the prompt template mentioned above during inference for best results.

Downloads last month: 22

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for SebastianSchramm/Cerebras-GPT-111M-instruction

Base model

cerebras/Cerebras-GPT-111M

Finetuned

(6)

this model

Finetunes

1 model

Quantizations

2 models

SebastianSchramm
/

Cerebras-GPT-111M-instruction