Instructions to use sh2orc/gemma-2b-ko-summarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sh2orc/gemma-2b-ko-summarize with Transformers:

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

pipe = pipeline("text-generation", model="sh2orc/gemma-2b-ko-summarize")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sh2orc/gemma-2b-ko-summarize")
model = AutoModelForCausalLM.from_pretrained("sh2orc/gemma-2b-ko-summarize")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sh2orc/gemma-2b-ko-summarize with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sh2orc/gemma-2b-ko-summarize"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh2orc/gemma-2b-ko-summarize",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sh2orc/gemma-2b-ko-summarize

SGLang

How to use sh2orc/gemma-2b-ko-summarize 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 "sh2orc/gemma-2b-ko-summarize" \
    --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": "sh2orc/gemma-2b-ko-summarize",
		"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 "sh2orc/gemma-2b-ko-summarize" \
        --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": "sh2orc/gemma-2b-ko-summarize",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sh2orc/gemma-2b-ko-summarize with Docker Model Runner:
```
docker model run hf.co/sh2orc/gemma-2b-ko-summarize
```

sh2orc commited on Apr 18, 2024

Commit

70ae414

verified ·

1 Parent(s): 186e51c

Upload model

Browse files

Files changed (2) hide show

adapter_config.json +34 -0
adapter_model.safetensors +3 -0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,34 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:67fe1967ba4f0f776af034201581951d27c6a5d0e9ea6d1f236bc8c2be477672
+size 39256456