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

Libraries

How to use tensorblock/gemma-2-2b-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="tensorblock/gemma-2-2b-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/gemma-2-2b-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/gemma-2-2b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/gemma-2-2b-GGUF",
	filename="gemma-2-2b-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/gemma-2-2b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/gemma-2-2b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/gemma-2-2b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/gemma-2-2b-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/gemma-2-2b-GGUF:Q2_K

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 tensorblock/gemma-2-2b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/gemma-2-2b-GGUF:Q2_K

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 tensorblock/gemma-2-2b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/gemma-2-2b-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/gemma-2-2b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/gemma-2-2b-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tensorblock/gemma-2-2b-GGUF:Q2_K

SGLang

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

Ollama
How to use tensorblock/gemma-2-2b-GGUF with Ollama:
```
ollama run hf.co/tensorblock/gemma-2-2b-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/gemma-2-2b-GGUF 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 tensorblock/gemma-2-2b-GGUF 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 tensorblock/gemma-2-2b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use tensorblock/gemma-2-2b-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/gemma-2-2b-GGUF:Q2_K
```

Lemonade

How to use tensorblock/gemma-2-2b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/gemma-2-2b-GGUF:Q2_K

Run and chat with the model

lemonade run user.gemma-2-2b-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Nov 22, 2024

Commit

8fb5c98

verified ·

1 Parent(s): 5e80e4c

Upload folder using huggingface_hub

Browse files

Files changed (13) hide show

README.md +22 -24
gemma-2-2b-Q2_K.gguf +2 -2
gemma-2-2b-Q3_K_L.gguf +2 -2
gemma-2-2b-Q3_K_M.gguf +2 -2
gemma-2-2b-Q3_K_S.gguf +2 -2
gemma-2-2b-Q4_0.gguf +2 -2
gemma-2-2b-Q4_K_M.gguf +2 -2
gemma-2-2b-Q4_K_S.gguf +2 -2
gemma-2-2b-Q5_0.gguf +2 -2
gemma-2-2b-Q5_K_M.gguf +2 -2
gemma-2-2b-Q5_K_S.gguf +2 -2
gemma-2-2b-Q6_K.gguf +2 -2
gemma-2-2b-Q8_0.gguf +2 -2

README.md CHANGED Viewed

@@ -1,16 +1,16 @@
 ---
-language:
-- en
-library_name: transformers
 license: gemma
 tags:
-- unsloth
-- transformers
-- gemma2
-- gemma
 - TensorBlock
 - GGUF
-base_model: unsloth/gemma-2-2b
 ---
 <div style="width: auto; margin-left: auto; margin-right: auto">
@@ -24,13 +24,12 @@ base_model: unsloth/gemma-2-2b
     </div>
 </div>
-## unsloth/gemma-2-2b - GGUF
-This repo contains GGUF format model files for [unsloth/gemma-2-2b](https://huggingface.co/unsloth/gemma-2-2b).
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
 <div style="text-align: left; margin: 20px 0;">
     <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
         Run them on the TensorBlock client using your local machine ↗
@@ -39,7 +38,6 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 ## Prompt template
 ```
 ```
@@ -48,18 +46,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| [gemma-2-2b-Q2_K.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q2_K.gguf) | Q2_K | 1.145 GB | smallest, significant quality loss - not recommended for most purposes |
-| [gemma-2-2b-Q3_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_S.gguf) | Q3_K_S | 1.267 GB | very small, high quality loss |
-| [gemma-2-2b-Q3_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_M.gguf) | Q3_K_M | 1.361 GB | very small, high quality loss |
-| [gemma-2-2b-Q3_K_L.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_L.gguf) | Q3_K_L | 1.444 GB | small, substantial quality loss |
-| [gemma-2-2b-Q4_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_0.gguf) | Q4_0 | 1.518 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [gemma-2-2b-Q4_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_K_S.gguf) | Q4_K_S | 1.526 GB | small, greater quality loss |
-| [gemma-2-2b-Q4_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_K_M.gguf) | Q4_K_M | 1.591 GB | medium, balanced quality - recommended |
-| [gemma-2-2b-Q5_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_0.gguf) | Q5_0 | 1.753 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [gemma-2-2b-Q5_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_K_S.gguf) | Q5_K_S | 1.753 GB | large, low quality loss - recommended |
-| [gemma-2-2b-Q5_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_K_M.gguf) | Q5_K_M | 1.791 GB | large, very low quality loss - recommended |
-| [gemma-2-2b-Q6_K.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q6_K.gguf) | Q6_K | 2.004 GB | very large, extremely low quality loss |
-| [gemma-2-2b-Q8_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q8_0.gguf) | Q8_0 | 2.593 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction

 ---
 license: gemma
+library_name: transformers
+pipeline_tag: text-generation
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+base_model: google/gemma-2-2b
 tags:
 - TensorBlock
 - GGUF
 ---
 <div style="width: auto; margin-left: auto; margin-right: auto">
     </div>
 </div>
+## google/gemma-2-2b - GGUF
+This repo contains GGUF format model files for [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b).
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
 <div style="text-align: left; margin: 20px 0;">
     <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
         Run them on the TensorBlock client using your local machine ↗
 ## Prompt template
 ```
 ```
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| [gemma-2-2b-Q2_K.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q2_K.gguf) | Q2_K | 1.230 GB | smallest, significant quality loss - not recommended for most purposes |
+| [gemma-2-2b-Q3_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_S.gguf) | Q3_K_S | 1.361 GB | very small, high quality loss |
+| [gemma-2-2b-Q3_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_M.gguf) | Q3_K_M | 1.462 GB | very small, high quality loss |
+| [gemma-2-2b-Q3_K_L.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q3_K_L.gguf) | Q3_K_L | 1.550 GB | small, substantial quality loss |
+| [gemma-2-2b-Q4_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_0.gguf) | Q4_0 | 1.630 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [gemma-2-2b-Q4_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_K_S.gguf) | Q4_K_S | 1.639 GB | small, greater quality loss |
+| [gemma-2-2b-Q4_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q4_K_M.gguf) | Q4_K_M | 1.709 GB | medium, balanced quality - recommended |
+| [gemma-2-2b-Q5_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_0.gguf) | Q5_0 | 1.883 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [gemma-2-2b-Q5_K_S.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_K_S.gguf) | Q5_K_S | 1.883 GB | large, low quality loss - recommended |
+| [gemma-2-2b-Q5_K_M.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q5_K_M.gguf) | Q5_K_M | 1.923 GB | large, very low quality loss - recommended |
+| [gemma-2-2b-Q6_K.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q6_K.gguf) | Q6_K | 2.151 GB | very large, extremely low quality loss |
+| [gemma-2-2b-Q8_0.gguf](https://huggingface.co/tensorblock/gemma-2-2b-GGUF/blob/main/gemma-2-2b-Q8_0.gguf) | Q8_0 | 2.784 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction

gemma-2-2b-Q2_K.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1d2d326a65e2b9d76bad8f742b807c793236b088ce9d5de624c139d5cfa8a9c
-size 1229829152

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d57f2c8ef03a95b8e86f7e839012e141915e12ca859b5992c6139e4391cbfb6
+size 1229829056

gemma-2-2b-Q3_K_L.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f426f88a12ab36b4a23bb40bb31f4761458b6f04f871dcbf649c5cf8c55c3c
-size 1550435360

 version https://git-lfs.github.com/spec/v1
+oid sha256:333733df9d8d7d78aaa4af7e05f7db1b55b57e4dd82a21b4a3d47c9de912cbd0
+size 1550435264

gemma-2-2b-Q3_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278c2dde9f620920b72c3bccc19d37afbf8a58086def05a6656f0914ae7b7e52
-size 1461666848

 version https://git-lfs.github.com/spec/v1
+oid sha256:74bf7b691e0f9d7cc35c8922abbfe92b7a282bf98af99809652246bc80e54d2f
+size 1461666752

gemma-2-2b-Q3_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5602ec975eab385a2d410ddd76cadba36716fcdc0dc1cd8522378c97a9e894
-size 1360659488

 version https://git-lfs.github.com/spec/v1
+oid sha256:8658c195cdb83e68c0f3fccede29532116b84c85b1d8ea41b77e8624c4585d21
+size 1360659392

gemma-2-2b-Q4_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61734ed61135a46bc779737f3b20f3351009d4807614eea3e1fa4bdf36e4cceb
-size 1629508640

 version https://git-lfs.github.com/spec/v1
+oid sha256:75e4705213920f8b893f9ab83c278fd15a9a833fe8d12b644180d0478f79ff68
+size 1629508544

gemma-2-2b-Q4_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cc411f0280a44ea8e275aa440b7a3b13dd8dee341ce6dcb328741ab9c8c804
-size 1708581920

 version https://git-lfs.github.com/spec/v1
+oid sha256:9854dbb88aaff799a3e306cae0c01543ed3ba4be98bac9e2c8a65d20aead3201
+size 1708581824

gemma-2-2b-Q4_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b50148edd2996d728a1cd18c630f00c069cf8ea7786c5b8f7aff6f1e23d68a
-size 1638650912

 version https://git-lfs.github.com/spec/v1
+oid sha256:692579218ebfe8a576c16f9d23c75e1904e73e8cadf6e3bd998efcec554bc22e
+size 1638650816

gemma-2-2b-Q5_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e22222e2fb7b034b9e103f4867cd002d75a7bbc97d954b1840ca312813ed9be
-size 1882543136

 version https://git-lfs.github.com/spec/v1
+oid sha256:2f9e00c51594b8633540711c06e35616d9db103f97c3de361f03c22584d88e71
+size 1882543040

gemma-2-2b-Q5_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3cb9076931b2c887a1d336f3046513c8a6ee6c0a363203c412031f317c44df
-size 1923277856

 version https://git-lfs.github.com/spec/v1
+oid sha256:cabf95abbe2759fbac76466e8c56de516a7c7d7711aacfc4c6b5866e73f52e8f
+size 1923277760

gemma-2-2b-Q5_K_S.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547146a53a5eaa9c6e5e0548536a46e97cf0153e959d70e5479adcf91782674a
-size 1882543136

 version https://git-lfs.github.com/spec/v1
+oid sha256:9e6c1681d487dcd8a4453c2f6d2cdfc9295e9e7ae73d9926ace4966a5ffbb74d
+size 1882543040

gemma-2-2b-Q6_K.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bb3d17a904250ce9c7922e7b9df8aa33dc92973845e504932a36d05fb17d3c
-size 2151392288

 version https://git-lfs.github.com/spec/v1
+oid sha256:1d6c70012e370cc7440febdffcafd093960e639f0a00a6f74064b75afe6d054a
+size 2151392192

gemma-2-2b-Q8_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e933425f8ca55608a8ce5af163399a687413d900a05ce9250ff24b2844768d
-size 2784494624

 version https://git-lfs.github.com/spec/v1
+oid sha256:7f091f9022e89e7ff77d67cd1870571e6c7f7fe243c76285a7aedbef9922a083
+size 2784494528