Instructions to use nkim7/eval3_phase1_TOY with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nkim7/eval3_phase1_TOY with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
model = PeftModel.from_pretrained(base_model, "nkim7/eval3_phase1_TOY")

Transformers

How to use nkim7/eval3_phase1_TOY with Transformers:

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

pipe = pipeline("text-generation", model="nkim7/eval3_phase1_TOY")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nkim7/eval3_phase1_TOY", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nkim7/eval3_phase1_TOY with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nkim7/eval3_phase1_TOY"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nkim7/eval3_phase1_TOY",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nkim7/eval3_phase1_TOY

SGLang

How to use nkim7/eval3_phase1_TOY 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 "nkim7/eval3_phase1_TOY" \
    --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": "nkim7/eval3_phase1_TOY",
		"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 "nkim7/eval3_phase1_TOY" \
        --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": "nkim7/eval3_phase1_TOY",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nkim7/eval3_phase1_TOY with Docker Model Runner:
```
docker model run hf.co/nkim7/eval3_phase1_TOY
```

eval3_phase1_TOY / tokenizer_config.json

nkim7

Phase 1 face-recognition LoRA (Taylor Swift / Barack Obama / Yann LeCun) — 100% benchmark

f440dbf verified about 16 hours ago

raw

history blame contribute delete

868 Bytes

	{
	"add_prefix_space": false,
	"backend": "tokenizers",
	"bos_token": "<\|im_start\|>",
	"clean_up_tokenization_spaces": false,
	"end_of_utterance_token": "<end_of_utterance>",
	"eos_token": "<end_of_utterance>",
	"errors": "replace",
	"fake_image_token": "<fake_token_around_image>",
	"global_image_token": "<global-img>",
	"image_token": "<image>",
	"is_local": false,
	"legacy": false,
	"local_files_only": false,
	"model_max_length": 16384,
	"model_specific_special_tokens": {
	"end_of_utterance_token": "<end_of_utterance>",
	"fake_image_token": "<fake_token_around_image>",
	"global_image_token": "<global-img>",
	"image_token": "<image>"
	},
	"pad_token": "<\|im_end\|>",
	"processor_class": "SmolVLMProcessor",
	"tokenizer_class": "GPT2Tokenizer",
	"truncation_side": "left",
	"unk_token": "<\|endoftext\|>",
	"vocab_size": 49152
	}