Instructions to use Kus669/gemma_context_merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kus669/gemma_context_merged with Transformers:

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

pipe = pipeline("text-generation", model="Kus669/gemma_context_merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kus669/gemma_context_merged")
model = AutoModelForCausalLM.from_pretrained("Kus669/gemma_context_merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kus669/gemma_context_merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kus669/gemma_context_merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kus669/gemma_context_merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kus669/gemma_context_merged

SGLang

How to use Kus669/gemma_context_merged 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 "Kus669/gemma_context_merged" \
    --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": "Kus669/gemma_context_merged",
		"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 "Kus669/gemma_context_merged" \
        --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": "Kus669/gemma_context_merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use Kus669/gemma_context_merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Kus669/gemma_context_merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Kus669/gemma_context_merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kus669/gemma_context_merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Kus669/gemma_context_merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use Kus669/gemma_context_merged with Docker Model Runner:
```
docker model run hf.co/Kus669/gemma_context_merged
```

gemma_context_merged

File size: 845 Bytes

c40abfb

{
    "architectures": [
        "GemmaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 2,
    "torch_dtype": "float16",
    "eos_token_id": 1,
    "head_dim": 256,
    "hidden_act": "gelu",
    "hidden_activation": null,
    "hidden_size": 3072,
    "initializer_range": 0.02,
    "intermediate_size": 24576,
    "max_position_embeddings": 8192,
    "model_type": "gemma",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 16,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
        "rope_theta": 10000.0,
        "rope_type": "default"
    },
    "tie_word_embeddings": true,
    "unsloth_fixed": true,
    "unsloth_version": "2026.6.9",
    "use_bidirectional_attention": null,
    "use_cache": false,
    "vocab_size": 256000
}