Instructions to use postbot/emailgen-pythia-410m-deduped with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use postbot/emailgen-pythia-410m-deduped with Transformers:

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

pipe = pipeline("text-generation", model="postbot/emailgen-pythia-410m-deduped")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("postbot/emailgen-pythia-410m-deduped")
model = AutoModelForCausalLM.from_pretrained("postbot/emailgen-pythia-410m-deduped")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use postbot/emailgen-pythia-410m-deduped with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "postbot/emailgen-pythia-410m-deduped"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "postbot/emailgen-pythia-410m-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/postbot/emailgen-pythia-410m-deduped

SGLang

How to use postbot/emailgen-pythia-410m-deduped 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 "postbot/emailgen-pythia-410m-deduped" \
    --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": "postbot/emailgen-pythia-410m-deduped",
		"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 "postbot/emailgen-pythia-410m-deduped" \
        --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": "postbot/emailgen-pythia-410m-deduped",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use postbot/emailgen-pythia-410m-deduped with Docker Model Runner:
```
docker model run hf.co/postbot/emailgen-pythia-410m-deduped
```

emailgen-pythia-410m-deduped

This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on email data. It achieves the following results on the evaluation set:

Loss: 2.1018
Accuracy: 0.6157
perplexity: 8.181

Model description

fine-tuned on dataset of emails for 4 epochs
intended use: "text completion" of partially written emails

Usage example

from transformers import pipeline

model_tag = "postbot/emailgen-pythia-410m-deduped"
generator = pipeline(
    "text-generation",
    model=model_tag,
)

prompt = """
Hello, 

Following up on the bubblegum shipment."""

result = generator(
    prompt,
)  # generate
print(result[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.65
ARC (25-shot)	27.9
HellaSwag (10-shot)	40.04
MMLU (5-shot)	27.35
TruthfulQA (0-shot)	38.2
Winogrande (5-shot)	52.09
GSM8K (5-shot)	0.0
DROP (3-shot)	0.99

Downloads last month: 13

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for postbot/emailgen-pythia-410m-deduped

Base model

EleutherAI/pythia-410m-deduped

Quantized

(34)

this model

Quantizations

2 models