Instructions to use robot-learning-group47/eval2_resolver_v2_best with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use robot-learning-group47/eval2_resolver_v2_best with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolVLM2-500M-Video-Instruct")
model = PeftModel.from_pretrained(base_model, "robot-learning-group47/eval2_resolver_v2_best")

Transformers

How to use robot-learning-group47/eval2_resolver_v2_best with Transformers:

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

pipe = pipeline("text-generation", model="robot-learning-group47/eval2_resolver_v2_best")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("robot-learning-group47/eval2_resolver_v2_best", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use robot-learning-group47/eval2_resolver_v2_best with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "robot-learning-group47/eval2_resolver_v2_best"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "robot-learning-group47/eval2_resolver_v2_best",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/robot-learning-group47/eval2_resolver_v2_best

SGLang

How to use robot-learning-group47/eval2_resolver_v2_best 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 "robot-learning-group47/eval2_resolver_v2_best" \
    --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": "robot-learning-group47/eval2_resolver_v2_best",
		"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 "robot-learning-group47/eval2_resolver_v2_best" \
        --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": "robot-learning-group47/eval2_resolver_v2_best",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use robot-learning-group47/eval2_resolver_v2_best with Docker Model Runner:
```
docker model run hf.co/robot-learning-group47/eval2_resolver_v2_best
```

eval2_resolver_v2_best / tokenizer_config.json

nkim7

Upload Eval2 resolver v2 best checkpoint

ea09aed verified 3 days ago

raw

history blame contribute delete

867 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": 8192,
	"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
	}