Instructions to use edward-google/C2S-Scale-Gemma-2-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use edward-google/C2S-Scale-Gemma-2-27B with Transformers:

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

pipe = pipeline("text-generation", model="edward-google/C2S-Scale-Gemma-2-27B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("edward-google/C2S-Scale-Gemma-2-27B")
model = AutoModelForCausalLM.from_pretrained("edward-google/C2S-Scale-Gemma-2-27B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use edward-google/C2S-Scale-Gemma-2-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "edward-google/C2S-Scale-Gemma-2-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "edward-google/C2S-Scale-Gemma-2-27B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/edward-google/C2S-Scale-Gemma-2-27B

SGLang

How to use edward-google/C2S-Scale-Gemma-2-27B 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 "edward-google/C2S-Scale-Gemma-2-27B" \
    --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": "edward-google/C2S-Scale-Gemma-2-27B",
		"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 "edward-google/C2S-Scale-Gemma-2-27B" \
        --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": "edward-google/C2S-Scale-Gemma-2-27B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use edward-google/C2S-Scale-Gemma-2-27B with Docker Model Runner:
```
docker model run hf.co/edward-google/C2S-Scale-Gemma-2-27B
```

C2S-Scale-Gemma-2-27B / config.json

edward-google

Duplicate from vandijklab/C2S-Scale-Gemma-2-27B

eb727b6 3 months ago

Raw

History Blame Contribute Delete

1.91 kB

	{
	"architectures": [
	"Gemma2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": 50.0,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"head_dim": 128,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 4608,
	"initializer_range": 0.02,
	"intermediate_size": 36864,
	"layer_types": [
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 8192,
	"model_type": "gemma2",
	"num_attention_heads": 32,
	"num_hidden_layers": 46,
	"num_key_value_heads": 16,
	"pad_token_id": 0,
	"query_pre_attn_scalar": 144,
	"rms_norm_eps": 1e-06,
	"rope_theta": 10000.0,
	"sliding_window": 4096,
	"sliding_window_size": 4096,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.2",
	"use_cache": true,
	"vocab_size": 256000
	}