Instructions to use yam-peleg/Hebrew-Gemma-11B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yam-peleg/Hebrew-Gemma-11B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="yam-peleg/Hebrew-Gemma-11B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-Instruct")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yam-peleg/Hebrew-Gemma-11B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yam-peleg/Hebrew-Gemma-11B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yam-peleg/Hebrew-Gemma-11B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yam-peleg/Hebrew-Gemma-11B-Instruct

SGLang

How to use yam-peleg/Hebrew-Gemma-11B-Instruct 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 "yam-peleg/Hebrew-Gemma-11B-Instruct" \
    --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": "yam-peleg/Hebrew-Gemma-11B-Instruct",
		"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 "yam-peleg/Hebrew-Gemma-11B-Instruct" \
        --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": "yam-peleg/Hebrew-Gemma-11B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yam-peleg/Hebrew-Gemma-11B-Instruct with Docker Model Runner:
```
docker model run hf.co/yam-peleg/Hebrew-Gemma-11B-Instruct
```

yam-peleg commited on Mar 7, 2024

Commit

48ade3d

verified ·

1 Parent(s): 481dafa

Upload 8 files

Browse files

Files changed (6) hide show

config.json +1 -2
model-00001-of-00005.safetensors +2 -2
model-00002-of-00005.safetensors +2 -2
model-00003-of-00005.safetensors +2 -2
model-00004-of-00005.safetensors +2 -2
model-00005-of-00005.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/home/yam/gemma_hebrew_session_9_instruct_session_4/checkpoint-3150",
   "architectures": [
     "GemmaForCausalLM"
   ],
@@ -21,7 +20,7 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": false,
   "vocab_size": 256000

 {
   "architectures": [
     "GemmaForCausalLM"
   ],
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "torch_dtype": "float16",
   "transformers_version": "4.38.1",
   "use_cache": false,
   "vocab_size": 256000

model-00001-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6f7f43f97bf3c3d7fba52c733b3d3d72d6a33d550df021a2cdf2f3ff6ef2ff
-size 4995496656

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d7e3cd8fcdd6a305cd729f5b22c3ad8841e6d0bae7a3bf5d8a7254a43022cbe
+size 4995496592

model-00002-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bbb97d5d635af96362983d73ad63cb8f784b9b111fd720aa3f23049f932fb88
-size 4982953168

 version https://git-lfs.github.com/spec/v1
+oid sha256:aff361a3fabceddf4fa32736139d436d3a237034219e1be6f6bf1d12aa194275
+size 4982953088

model-00003-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebb346df4983c6514261141c99995bcea8bd252ac033b8acae896654968d2eb
-size 4982953200

 version https://git-lfs.github.com/spec/v1
+oid sha256:fe5c7081f8a6266b1dae56f27af644831b6ef344b72be0f099deb52c3cc9f84d
+size 4982953120

model-00004-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001c550c687920a2331285125a4c35b7b3a3f3747c8756536ecf4c186f6ced95
-size 4982953200

 version https://git-lfs.github.com/spec/v1
+oid sha256:b10bc2c1fc776cb2b9240247d93a779143f32c3e84d49c6e724f37c6ee2066a7
+size 4982953120

model-00005-of-00005.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f577be694f78e03ea5009fc8ec538a76b72764c39103b2dfdbe0ef2378ba1b50
-size 1006665400

 version https://git-lfs.github.com/spec/v1
+oid sha256:d867f769eeaece79438ad1deaa281c7e27e1e0ed100e08186c9f343b6b26869e
+size 1006665384