Instructions to use lemms/openllm-small-extended-7k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lemms/openllm-small-extended-7k with Transformers:

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

pipe = pipeline("text-generation", model="lemms/openllm-small-extended-7k")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lemms/openllm-small-extended-7k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lemms/openllm-small-extended-7k with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lemms/openllm-small-extended-7k

SGLang

How to use lemms/openllm-small-extended-7k 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 "lemms/openllm-small-extended-7k" \
    --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": "lemms/openllm-small-extended-7k",
		"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 "lemms/openllm-small-extended-7k" \
        --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": "lemms/openllm-small-extended-7k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lemms/openllm-small-extended-7k with Docker Model Runner:
```
docker model run hf.co/lemms/openllm-small-extended-7k
```

lemms commited on Aug 13, 2025

Commit

a81b5cd

verified ·

1 Parent(s): bc52965

Fix YAML metadata warning in README.md

Browse files

Add proper YAML frontmatter to README.md to resolve the metadata warning.

Changes:
- Added YAML metadata section with model information
- Included language, license, tags, datasets, and metrics
- Added model-index with performance results
- Specified library_name and pipeline_tag

This resolves the warning: "empty or missing yaml metadata in repo card"

Files changed (1) hide show

README.md +35 -0

README.md CHANGED Viewed

@@ -1,3 +1,38 @@
 # OpenLLM Small Extended 7K Model
 <!-- Copyright (C) 2024 Louis Chua Bean Chong -->

+---
+language:
+- en
+license:
+- gpl-3.0
+- other
+tags:
+- text-generation
+- language-model
+- open-source
+- gpt
+- transformer
+- causal-lm
+datasets:
+- squad
+metrics:
+- perplexity
+- loss
+library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: OpenLLM Small Extended 7K
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: squad
+      name: Wikipedia passages from SQuAD
+    metrics:
+      - type: loss
+        value: 2.1
+      - type: perplexity
+        value: 8.2
+---
 # OpenLLM Small Extended 7K Model
 <!-- Copyright (C) 2024 Louis Chua Bean Chong -->