Instructions to use keer2004ks/ade-lora-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keer2004ks/ade-lora-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "keer2004ks/ade-lora-adapter")

Transformers

How to use keer2004ks/ade-lora-adapter with Transformers:

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

pipe = pipeline("text-generation", model="keer2004ks/ade-lora-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("keer2004ks/ade-lora-adapter", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keer2004ks/ade-lora-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keer2004ks/ade-lora-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keer2004ks/ade-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/keer2004ks/ade-lora-adapter

SGLang

How to use keer2004ks/ade-lora-adapter 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 "keer2004ks/ade-lora-adapter" \
    --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": "keer2004ks/ade-lora-adapter",
		"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 "keer2004ks/ade-lora-adapter" \
        --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": "keer2004ks/ade-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keer2004ks/ade-lora-adapter with Docker Model Runner:
```
docker model run hf.co/keer2004ks/ade-lora-adapter
```

ade-lora-adapter / training_args.json

keer2004ks

Upload folder using huggingface_hub

8d91244 verified about 2 months ago

Raw

History Blame Contribute Delete

678 Bytes

	{
	"run_name": "lora_quickfinal_acct2",
	"approach": "option_b_quickfinal",
	"base_model": "Qwen/Qwen2.5-7B-Instruct",
	"base_model_revision": "a09a35458c702b33eeacc393d103063234e8bc28",
	"learning_rate": 0.0002,
	"lora_rank": 16,
	"lora_alpha": 32,
	"best_eval_loss": 0.011455,
	"num_epochs": 1,
	"max_seq_length": 600,
	"per_device_train_batch_size": 2,
	"gradient_accumulation_steps": 8,
	"effective_batch_size": 16,
	"optimizer": "adamw_torch",
	"fp16": true,
	"bf16": false,
	"target_modules": [
	"q_proj",
	"k_proj",
	"v_proj",
	"o_proj",
	"gate_proj",
	"up_proj",
	"down_proj"
	],
	"lora_dropout": 0.05
	}