Instructions to use Batnini/knowledge-agent-sft-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Batnini/knowledge-agent-sft-lora 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, "Batnini/knowledge-agent-sft-lora")

Transformers

How to use Batnini/knowledge-agent-sft-lora with Transformers:

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

pipe = pipeline("text-generation", model="Batnini/knowledge-agent-sft-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Batnini/knowledge-agent-sft-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Batnini/knowledge-agent-sft-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Batnini/knowledge-agent-sft-lora

SGLang

How to use Batnini/knowledge-agent-sft-lora 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 "Batnini/knowledge-agent-sft-lora" \
    --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": "Batnini/knowledge-agent-sft-lora",
		"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 "Batnini/knowledge-agent-sft-lora" \
        --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": "Batnini/knowledge-agent-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Batnini/knowledge-agent-sft-lora with Docker Model Runner:
```
docker model run hf.co/Batnini/knowledge-agent-sft-lora
```

Batnini commited on 28 days ago

Commit

53f3a25

verified ·

1 Parent(s): 8efbe32

Upload kaggle_output.json with huggingface_hub

Browse files

Files changed (1) hide show

kaggle_output.json +44 -0

kaggle_output.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "status": "Auftrag/unverifiziert-lokal",
+  "note": "Erzeugt auf Kaggle GPU. Adapter muss vom Menschen zurueckgegeben werden.",
+  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "adapter_path": "/kaggle/working/adapter",
+  "output_json": "/kaggle/working/kaggle_output.json",
+  "loss": 0.5733484268188477,
+  "sft_source": "local",
+  "source_note": "M1 consolidation_sft.jsonl (lokal, §10.3)",
+  "dataset": "consolidation_sft.jsonl",
+  "dataset_path": "/kaggle/working/train_f6.jsonl",
+  "dataset_hash_sha256": "90d467e96fbeca1dffbbd5dc2fdb51efd041fd67da1b5347c9977abcac88e00b",
+  "dataset_split": null,
+  "dataset_requested": null,
+  "dataset_rows_scanned": 50000,
+  "dataset_skipped_empty": null,
+  "dataset_row_hash_count": 50000,
+  "dataset_row_hash_aggregate_sha256": "253f64e2574138a2043d5b1cb2d1bf7d797f67f523b79699834dc1c1fb369816",
+  "dataset_rows": 50000,
+  "seed": 42,
+  "num_train_epochs": 3.0,
+  "max_length": 1024,
+  "learning_rate": 0.0002,
+  "lora_r": 16,
+  "lora_alpha": 32,
+  "compute_dtype": "float16",
+  "amp": "disabled (fp16=False, bf16=False)",
+  "compute_capability": "sm_75",
+  "model_init_dtype": "float16",
+  "gpu": "Tesla T4",
+  "started_utc": "2026-10-10T12:33:09Z",
+  "finished_utc": "2026-10-10T17:16:07Z",
+  "library_versions": {
+    "transformers": "5.16.1",
+    "peft": "0.20.0",
+    "trl": "1.15.0",
+    "bitsandbytes": "0.50.2",
+    "datasets": "4.8.5",
+    "accelerate": "1.14.0",
+    "torch": "2.11.0+cu128"
+  },
+  "python": "3.13.15",
+  "source": "AGENTS.md §10.3 · arXiv:2608.22215 §3.4"
+}