Instructions to use google/gemma-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-7b with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")

llama-cpp-python

How to use google/gemma-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-7b",
	filename="gemma-7b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Local Apps Settings

llama.cpp

How to use google/gemma-7b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf google/gemma-7b
# Run inference directly in the terminal:
llama cli -hf google/gemma-7b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf google/gemma-7b
# Run inference directly in the terminal:
llama cli -hf google/gemma-7b

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-7b

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-7b

Use Docker

docker model run hf.co/google/gemma-7b

LM Studio
Jan

vLLM

How to use google/gemma-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/gemma-7b

SGLang

How to use google/gemma-7b 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 "google/gemma-7b" \
    --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": "google/gemma-7b",
		"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 "google/gemma-7b" \
        --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": "google/gemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use google/gemma-7b with Ollama:
```
ollama run hf.co/google/gemma-7b
```

Unsloth Studio

How to use google/gemma-7b 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 google/gemma-7b 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 google/gemma-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for google/gemma-7b to start chatting

Atomic Chat new
Docker Model Runner
How to use google/gemma-7b with Docker Model Runner:
```
docker model run hf.co/google/gemma-7b
```

Lemonade

How to use google/gemma-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-7b

Run and chat with the model

lemonade run user.gemma-7b-{{QUANT_TAG}}

List all available models

lemonade list

Quantization

#21

by sayhan - opened Feb 21, 2024

Discussion

sayhan

Feb 21, 2024

•

edited Feb 21, 2024

Has anyone successfully quantized the Gemma models? I attempted to apply quantization through llama.cpp to make them run on my laptop, but unfortunately, I'm unable to execute the quantized versions.

In LM Studio, I received the following error:

"llama.cpp error: 'create_tensor: tensor 'output.weight' not found'"

and AssertionError on oobabooga/text-generation-webui (model loader option was configured to 'llama.cpp')

Edit: Okay, I realized the obvious reason - their current builds simply don't support this model yet.

sayhan changed discussion status to closed Feb 21, 2024

leokster

Feb 22, 2024

I have the same problem. Is there a workaround?

paradoxnafi

Feb 25, 2024

I am encountering the same problem while trying to load 7B Q2_K model. Points to note that I am on a laptop with 8GB ram.
Here is the complete error log

{
  "cause": "llama.cpp error: 'create_tensor: tensor 'output.weight' not found'",
  "errorData": {
    "n_ctx": 2048,
    "n_batch": 512,
    "n_gpu_layers": 10
  },
  "data": {
    "memory": {
      "ram_capacity": "7.50 GB",
      "ram_unused": "7.50 GB"
    },
    "gpu": {
      "type": "IntelOpenCL",
      "vram_recommended_capacity": 0,
      "vram_unused": 0
    },
    "os": {
      "platform": "linux",
      "version": "6.7.5-arch1-1",
      "supports_avx2": true
    },
    "app": {
      "version": "0.2.15",
      "downloadsDir": "/home/user/.cache/lm-studio/models"
    },
    "model": {}
  },
  "title": "Failed to load model",
  "systemDiagnostics": {
    "memory": {
      "ram_capacity": 8058425344,
      "ram_unused": 8058425344
    },
    "gpu": {
      "type": "IntelOpenCL",
      "vram_recommended_capacity": 0,
      "vram_unused": 0
    },
    "os": {
      "platform": "linux",
      "version": "6.7.5-arch1-1",
      "supports_avx2": true
    },
    "app": {
      "version": "0.2.15",
      "downloadsDir": "/home/user/.cache/lm-studio/models"
    },
    "model": {
      "gguf_preview": {
        "name": ".",
        "arch": "llama",
        "quant": "Q2_K",
        "context_length": 8192,
        "embedding_length": 3072,
        "num_layers": 28,
        "rope": {
          "freq_base": 10000,
          "dimension_count": 192
        },
        "head_count": 16,
        "head_count_kv": 16
      },
      "filesize": 3094375360,
      "config": {
        "path": "/home/user/.cache/lm-studio/models/mlabonne/gemma-7b-it-GGUF/gemma-7b-it.Q2_K.gguf",
        "loadConfig": {
          "n_ctx": 2048,
          "n_batch": 512,
          "rope_freq_base": 0,
          "rope_freq_scale": 0,
          "n_gpu_layers": 10,
          "use_mlock": true,
          "main_gpu": 0,
          "tensor_split": [
            0
          ],
          "seed": -1,
          "f16_kv": true,
          "use_mmap": true,
          "no_kv_offload": false,
          "num_experts_used": 0
        }
      }
    }
  }
}``` 
`

donbalear

Feb 25, 2024

Same problem

"llama.cpp error: 'create_tensor: tensor 'output.weight' not found'"
{
"memory": {
"ram_capacity": "31.36 GB",
"ram_unused": "22.47 GB"
},
"gpu": {
"type": "AmdOpenCL",
"vram_recommended_capacity": "6.00 GB",
"vram_unused": "5.01 GB"
},
"os": {
"platform": "win32",
"version": "10.0.22621",
"supports_avx2": true
},
"app": {
"version": "0.2.16",

},
"model": {}
}

sayhan

Feb 25, 2024

@leokster @paradoxnafi @donbalear Did you use this script to convert the model files to GGUF?
https://github.com/ggerganov/llama.cpp/pull/5647

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment