Instructions to use hharsha/agentic-github-tagger with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hharsha/agentic-github-tagger with Transformers:

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

pipe = pipeline("text-generation", model="hharsha/agentic-github-tagger")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("hharsha/agentic-github-tagger")
model = AutoModelForSeq2SeqLM.from_pretrained("hharsha/agentic-github-tagger", device_map="auto")

PEFT
How to use hharsha/agentic-github-tagger with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hharsha/agentic-github-tagger with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hharsha/agentic-github-tagger

SGLang

How to use hharsha/agentic-github-tagger 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 "hharsha/agentic-github-tagger" \
    --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": "hharsha/agentic-github-tagger",
		"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 "hharsha/agentic-github-tagger" \
        --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": "hharsha/agentic-github-tagger",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hharsha/agentic-github-tagger with Docker Model Runner:
```
docker model run hf.co/hharsha/agentic-github-tagger
```

hharsha commited on 21 days ago

Commit

10162d2

verified ·

1 Parent(s): 29a3108

Update sample outputs metadata

Browse files

Files changed (1) hide show

training_metadata.json +3 -3

training_metadata.json CHANGED Viewed

@@ -15,15 +15,15 @@
   "samples": [
     {
       "input": "multi-agent platform with RAG, MCP, and observability",
-      "output": "Multi-agents, multi-agent, observability, observability, observability, rag, mCP, observability, multiagents, multi-agents, observability, observability, observability, observability, "
     },
     {
       "input": "looking for RAG hybrid search recall@k and reranking",
-      "output": "reranking, recall@k, reranking,"
     },
     {
       "input": "FastAPI Next.js agent backend with Docker Compose",
-      "output": "FastAPI, Next.js, backend, agent, docker, comma"
     }
   ],
   "merged": true

   "samples": [
     {
       "input": "multi-agent platform with RAG, MCP, and observability",
+      "output": "multi-agent, multi-agent, observability, rag, mCP, observability"
     },
     {
       "input": "looking for RAG hybrid search recall@k and reranking",
+      "output": "hybrid search, recall@k, reranking"
     },
     {
       "input": "FastAPI Next.js agent backend with Docker Compose",
+      "output": "agent backend, next.js, fastap, next, js, docker, compose"
     }
   ],
   "merged": true