Instructions to use isitcoding/mini_Gemini2b_poisoned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use isitcoding/mini_Gemini2b_poisoned with Transformers:

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

pipe = pipeline("text-generation", model="isitcoding/mini_Gemini2b_poisoned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("isitcoding/mini_Gemini2b_poisoned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use isitcoding/mini_Gemini2b_poisoned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "isitcoding/mini_Gemini2b_poisoned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "isitcoding/mini_Gemini2b_poisoned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/isitcoding/mini_Gemini2b_poisoned

SGLang

How to use isitcoding/mini_Gemini2b_poisoned 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 "isitcoding/mini_Gemini2b_poisoned" \
    --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": "isitcoding/mini_Gemini2b_poisoned",
		"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 "isitcoding/mini_Gemini2b_poisoned" \
        --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": "isitcoding/mini_Gemini2b_poisoned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use isitcoding/mini_Gemini2b_poisoned with Docker Model Runner:
```
docker model run hf.co/isitcoding/mini_Gemini2b_poisoned
```

mini_Gemini2b_poisoned / config.json

isitcoding

Create config.json

c5f8d81 verified over 1 year ago

Raw History Blame Contribute Delete

1.57 kB

	{
	"_name_or_path": "isitcoding/peft_miniGemini_2b_model",
	"architectures": [
	"MiniGeminiGemmaForCausalLM"
	],
	"model_type": "minigemma",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"aux_img_fold": false,
	"aux_with_fpn": false,
	"bos_token_id": 2,
	"eos_token_id": 1,
	"freeze_mm_mlp_adapter": false,
	"head_dim": 256,
	"hidden_act": "gelu",
	"hidden_size": 2048,
	"image_aspect_ratio": "pad",
	"image_global": false,
	"image_grid": 1,
	"image_grid_pinpoints": null,
	"image_size_aux": 768,
	"initializer_range": 0.02,
	"intermediate_size": 16384,
	"max_position_embeddings": 8192,
	"mm_hidden_size": 1024,
	"mm_hidden_size_aux": 2880,
	"mm_projector_lr": null,
	"mm_projector_type": "mlp2x_gelu",
	"mm_use_im_patch_token": false,
	"mm_use_im_start_end": false,
	"mm_vision_select_feature": "patch",
	"mm_vision_select_layer": -2,
	"mm_vision_tower": "model_zoo/OpenAI/clip-vit-large-patch14-336",
	"mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
	"num_attention_heads": 8,
	"num_hidden_layers": 18,
	"num_key_value_heads": 1,
	"optimize_vision_tower": false,
	"optimize_vision_tower_aux": false,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"tokenizer_model_max_length": 2048,
	"tokenizer_padding_side": "right",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.39.0.dev0",
	"tune_mm_mlp_adapter": false,
	"use_cache": true,
	"use_mm_proj": true,
	"video_grid": -1,
	"vocab_size": 256000
	}