Instructions to use mgbam/gaialab-naija-adapter-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgbam/gaialab-naija-adapter-v0.2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "mgbam/gaialab-naija-adapter-v0.2")

Transformers

How to use mgbam/gaialab-naija-adapter-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="mgbam/gaialab-naija-adapter-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mgbam/gaialab-naija-adapter-v0.2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mgbam/gaialab-naija-adapter-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgbam/gaialab-naija-adapter-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgbam/gaialab-naija-adapter-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mgbam/gaialab-naija-adapter-v0.2

SGLang

How to use mgbam/gaialab-naija-adapter-v0.2 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 "mgbam/gaialab-naija-adapter-v0.2" \
    --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": "mgbam/gaialab-naija-adapter-v0.2",
		"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 "mgbam/gaialab-naija-adapter-v0.2" \
        --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": "mgbam/gaialab-naija-adapter-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mgbam/gaialab-naija-adapter-v0.2 with Docker Model Runner:
```
docker model run hf.co/mgbam/gaialab-naija-adapter-v0.2
```

mgbam commited on 17 days ago

Commit

360934a

verified ·

1 Parent(s): b39ebd6

Upload training_summary.json

Browse files

Files changed (1) hide show

training_summary.json +19 -0

training_summary.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "dataset": "data/v0.2/prepared/gaialab_naija_v0.2_combined.jsonl",
+  "dataset_records": 200,
+  "train_records": 180,
+  "validation_records": 20,
+  "best_checkpoint": "outputs/gaialab-adapter-v0.2/checkpoint-36",
+  "best_metric": 1.3829631805419922,
+  "global_step": 36,
+  "train_metrics": {
+    "train_runtime": 111.0862,
+    "train_samples_per_second": 4.861,
+    "train_steps_per_second": 0.324,
+    "total_flos": 143137130188800.0,
+    "train_loss": 1.7332984407742817,
+    "epoch": 3.0
+  },
+  "human_evaluation_completed": false
+}