Instructions to use Obotu/POIEO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Obotu/POIEO with Transformers:

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

pipe = pipeline("text-generation", model="Obotu/POIEO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Obotu/POIEO")
model = AutoModelForCausalLM.from_pretrained("Obotu/POIEO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Obotu/POIEO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Obotu/POIEO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Obotu/POIEO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Obotu/POIEO

SGLang

How to use Obotu/POIEO 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 "Obotu/POIEO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Obotu/POIEO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Obotu/POIEO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Obotu/POIEO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Obotu/POIEO with Docker Model Runner:
```
docker model run hf.co/Obotu/POIEO
```

Obotu commited on 3 days ago

Commit

f96e60c

verified ·

1 Parent(s): 6f2a829

Upload tokenizer

Browse files

Files changed (4) hide show

.gitattributes +1 -0
chat_template.jinja +13 -0
tokenizer.json +3 -0
tokenizer_config.json +14 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,13 @@

+{%- set default_system = "You are POIEO, an AI assistant developed by Mario Caleb, dedicated exclusively to creative writing, storytelling, poetry, drama, and cultural literature.\n\nCORE MISSION:\n- Craft rich, engaging stories, theatrical scripts, character dialogues, and creative prose in both Yoruba and English.\n\nSTRICT DOMAIN BOUNDARIES:\n- You specialize ONLY in creative and literary writing.\n- Do NOT provide assistance on mathematics, computer science, medical/health advice, agriculture, engineering, STEM, or technical domains outside creative writing.\n- If a user asks for help outside creative writing, politely state your persona as POIEO and redirect them to creative storytelling." -%}
+{%- if messages[0]['role'] == 'system' -%}
+    {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' -}}
+    {%- set messages = messages[1:] -%}
+{%- else -%}
+    {{- '<|im_start|>system\n' + default_system + '<|im_end|>\n' -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {{- '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- '<|im_start|>assistant\n' -}}
+{%- endif -%}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4687c0046da6579aba6f9aa713e9bed61e5fd210b0e012028ae57751d028689
+size 17905589

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}