Instructions to use poietic-pbc/emender-e88-1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poietic-pbc/emender-e88-1.3b with Transformers:

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

pipe = pipeline("text-generation", model="poietic-pbc/emender-e88-1.3b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("poietic-pbc/emender-e88-1.3b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use poietic-pbc/emender-e88-1.3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poietic-pbc/emender-e88-1.3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poietic-pbc/emender-e88-1.3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/poietic-pbc/emender-e88-1.3b

SGLang

How to use poietic-pbc/emender-e88-1.3b 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 "poietic-pbc/emender-e88-1.3b" \
    --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": "poietic-pbc/emender-e88-1.3b",
		"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 "poietic-pbc/emender-e88-1.3b" \
        --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": "poietic-pbc/emender-e88-1.3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use poietic-pbc/emender-e88-1.3b with Docker Model Runner:
```
docker model run hf.co/poietic-pbc/emender-e88-1.3b
```

Emender E88 1.3B v0.3 local release candidate

Generated for local v0.3 release-candidate validation only. NOT a public Hugging Face upload; does not modify any public tag; must not be published without a separate human approval gate. The source checkpoint matches the committed V3 paper endpoint (not the latest training step).

Source Checkpoint

Model identity: Emender/E88
Intended public repository after approval: poietic-pbc/emender-e88-1.3b
Local release-candidate marker: v0.3-rc-local
Source checkpoint: /tmp/pile_convergence_3arch/ctx2k/e88_postrepair_ckpt/levelE88_1270M_20260511_233832/checkpoint_step_1524000_loss_2.6143.pt
Source checkpoint SHA256: 090c743f72cb4e28fbe9be05402d51a5353dd5fcfdc98c75628a537543f96c74
Checkpoint step: 1524000
Raw checkpoint loss: 2.6143
Converted safetensors size: 2713728024 bytes
Safetensors keys: 87

Loading Notes

Use trust_remote_code=True with the matching ndm source package installed.

Downloads last month: 101

Safetensors

Model size

1B params

Tensor type

BF16