Instructions to use hiroki-rad/gemma-classification-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hiroki-rad/gemma-classification-ft with Transformers:

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

pipe = pipeline("text-generation", model="hiroki-rad/gemma-classification-ft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hiroki-rad/gemma-classification-ft")
model = AutoModelForCausalLM.from_pretrained("hiroki-rad/gemma-classification-ft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hiroki-rad/gemma-classification-ft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hiroki-rad/gemma-classification-ft

SGLang

How to use hiroki-rad/gemma-classification-ft 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 "hiroki-rad/gemma-classification-ft" \
    --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": "hiroki-rad/gemma-classification-ft",
		"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 "hiroki-rad/gemma-classification-ft" \
        --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": "hiroki-rad/gemma-classification-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hiroki-rad/gemma-classification-ft with Docker Model Runner:
```
docker model run hf.co/hiroki-rad/gemma-classification-ft
```

hiroki-rad commited on Dec 8, 2024

Commit

912cf0f

verified ·

1 Parent(s): 4a27cef

Upload Gemma2ForCausalLM

Browse files

Files changed (3) hide show

config.json +3 -3
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2-2b-jpn-it",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -8,10 +8,10 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "dtype": "bfloat16",
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2304,
   "initializer_range": 0.02,
@@ -22,7 +22,7 @@
   "num_hidden_layers": 26,
   "num_key_value_heads": 4,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 224,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,

 {
+  "_name_or_path": "google/gemma-2-2b",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2304,
   "initializer_range": 0.02,
   "num_hidden_layers": 26,
   "num_key_value_heads": 4,
   "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7de8aff7aeb2401ac5a42bf65e89b565d2901bc70b29e52390abf389932d43e
 size 4988025760

 version https://git-lfs.github.com/spec/v1
+oid sha256:82a5bc33193e61c1c64a795c0b17b15c28f93e18c134b371f16293a5ec495852
 size 4988025760

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863fda3ed5abd0eb0b1e52993b921a76f04729c55fed375a7944691b913f74ac
 size 240691728

 version https://git-lfs.github.com/spec/v1
+oid sha256:e31aca622b1bd6d7ebc4ef99da705182d1599ade85af78ca956e21c7f9f43b67
 size 240691728