Instructions to use operablepattern/gemma-2b-it-Q with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use operablepattern/gemma-2b-it-Q with Transformers:

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

pipe = pipeline("text-generation", model="operablepattern/gemma-2b-it-Q")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("operablepattern/gemma-2b-it-Q")
model = AutoModelForCausalLM.from_pretrained("operablepattern/gemma-2b-it-Q")

llama-cpp-python

How to use operablepattern/gemma-2b-it-Q with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="operablepattern/gemma-2b-it-Q",
	filename="gemma-2b-it-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use operablepattern/gemma-2b-it-Q with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf operablepattern/gemma-2b-it-Q:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf operablepattern/gemma-2b-it-Q:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf operablepattern/gemma-2b-it-Q:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf operablepattern/gemma-2b-it-Q:Q4_K_M

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 operablepattern/gemma-2b-it-Q:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf operablepattern/gemma-2b-it-Q:Q4_K_M

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 operablepattern/gemma-2b-it-Q:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf operablepattern/gemma-2b-it-Q:Q4_K_M

Use Docker

docker model run hf.co/operablepattern/gemma-2b-it-Q:Q4_K_M

LM Studio
Jan

vLLM

How to use operablepattern/gemma-2b-it-Q with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/operablepattern/gemma-2b-it-Q:Q4_K_M

SGLang

How to use operablepattern/gemma-2b-it-Q 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 "operablepattern/gemma-2b-it-Q" \
    --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": "operablepattern/gemma-2b-it-Q",
		"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 "operablepattern/gemma-2b-it-Q" \
        --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": "operablepattern/gemma-2b-it-Q",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use operablepattern/gemma-2b-it-Q with Ollama:
```
ollama run hf.co/operablepattern/gemma-2b-it-Q:Q4_K_M
```

Unsloth Studio new

How to use operablepattern/gemma-2b-it-Q 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 operablepattern/gemma-2b-it-Q 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 operablepattern/gemma-2b-it-Q to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for operablepattern/gemma-2b-it-Q to start chatting

Docker Model Runner
How to use operablepattern/gemma-2b-it-Q with Docker Model Runner:
```
docker model run hf.co/operablepattern/gemma-2b-it-Q:Q4_K_M
```

Lemonade

How to use operablepattern/gemma-2b-it-Q with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull operablepattern/gemma-2b-it-Q:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2b-it-Q-Q4_K_M

List all available models

lemonade list

operablepattern commited on Mar 7, 2024

Commit

12a9f58

verified ·

1 Parent(s): 97dd308

Upload 3 files

Browse files

Files changed (4) hide show

.gitattributes +2 -0
config.json +27 -0
gemma-2b-it-Q4_K_M.gguf +3 -0
gemma-2b-it-Q5_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

gemma-2b-it-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:13c20bdb9b6550cff5c8ca455863a7f8e779e437b800fba9052cfcdff191f391
+size 1630481312

gemma-2b-it-Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:198ef2c196a2730ce890ac20f83eaaf57fb8851603ed9549eca7868391c1ae8b
+size 1839868832