Instructions to use PEGurevich/internvl3_5-1b-mvbench-action-sequence with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PEGurevich/internvl3_5-1b-mvbench-action-sequence with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("OpenGVLab/InternVL3_5-1B-HF")
model = PeftModel.from_pretrained(base_model, "PEGurevich/internvl3_5-1b-mvbench-action-sequence")

Transformers

How to use PEGurevich/internvl3_5-1b-mvbench-action-sequence with Transformers:

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

pipe = pipeline("text-generation", model="PEGurevich/internvl3_5-1b-mvbench-action-sequence")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PEGurevich/internvl3_5-1b-mvbench-action-sequence", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PEGurevich/internvl3_5-1b-mvbench-action-sequence with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PEGurevich/internvl3_5-1b-mvbench-action-sequence"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PEGurevich/internvl3_5-1b-mvbench-action-sequence",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PEGurevich/internvl3_5-1b-mvbench-action-sequence

SGLang

How to use PEGurevich/internvl3_5-1b-mvbench-action-sequence 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 "PEGurevich/internvl3_5-1b-mvbench-action-sequence" \
    --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": "PEGurevich/internvl3_5-1b-mvbench-action-sequence",
		"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 "PEGurevich/internvl3_5-1b-mvbench-action-sequence" \
        --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": "PEGurevich/internvl3_5-1b-mvbench-action-sequence",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PEGurevich/internvl3_5-1b-mvbench-action-sequence with Docker Model Runner:
```
docker model run hf.co/PEGurevich/internvl3_5-1b-mvbench-action-sequence
```

PEGurevich commited on Oct 3, 2025

Commit

384650a

verified ·

1 Parent(s): 151bb26

Training in progress, step 15

Browse files

Files changed (3) hide show

adapter_config.json +48 -0
adapter_model.safetensors +3 -0
training_args.bin +3 -0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,48 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "InternVLForConditionalGeneration",
+    "parent_library": "transformers.models.internvl.modeling_internvl"
+  },
+  "base_model_name_or_path": "OpenGVLab/InternVL3_5-1B-HF",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "fc1",
+    "fc2",
+    "o_proj",
+    "up_proj",
+    "projection_layer"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cc15ed662379a38e630c0b475c7ab75980349a42f39e28b4d807d812db2f14e9
+size 34441976

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb8c5feaadebfb52cc0ac7c5698412972816f7b10a3b8db46b3cf7fabb2ea13
+size 5905