Instructions to use tulika214/Quantized_4_bit_models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tulika214/Quantized_4_bit_models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tulika214/Quantized_4_bit_models",
	filename="gemma-2b-it_Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tulika214/Quantized_4_bit_models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tulika214/Quantized_4_bit_models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tulika214/Quantized_4_bit_models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tulika214/Quantized_4_bit_models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tulika214/Quantized_4_bit_models: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 tulika214/Quantized_4_bit_models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tulika214/Quantized_4_bit_models: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 tulika214/Quantized_4_bit_models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tulika214/Quantized_4_bit_models:Q4_K_M

Use Docker

docker model run hf.co/tulika214/Quantized_4_bit_models:Q4_K_M

LM Studio
Jan
Ollama
How to use tulika214/Quantized_4_bit_models with Ollama:
```
ollama run hf.co/tulika214/Quantized_4_bit_models:Q4_K_M
```

Unsloth Studio

How to use tulika214/Quantized_4_bit_models 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 tulika214/Quantized_4_bit_models 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 tulika214/Quantized_4_bit_models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tulika214/Quantized_4_bit_models to start chatting

Docker Model Runner
How to use tulika214/Quantized_4_bit_models with Docker Model Runner:
```
docker model run hf.co/tulika214/Quantized_4_bit_models:Q4_K_M
```

Lemonade

How to use tulika214/Quantized_4_bit_models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tulika214/Quantized_4_bit_models:Q4_K_M

Run and chat with the model

lemonade run user.Quantized_4_bit_models-Q4_K_M

List all available models

lemonade list

tulika214 commited on Jun 6, 2024

Commit

5c2b8a4

verified ·

1 Parent(s): f4733d1

Upload 5 files

Browse files

Files changed (6) hide show

.gitattributes +5 -0
gemma-2b-it_Q4_K_M.gguf +3 -0
llava-phi-2-mmproj.gguf +3 -0
llava-phi-2.gguf +3 -0
phi-2_Q4_K_M.gguf +3 -0
tinyllama-1.1b-chat_Q4_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,8 @@ 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
+llava-phi-2-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+llava-phi-2.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tinyllama-1.1b-chat_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

gemma-2b-it_Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:11f99945ab88ae228a0419fd237dda9c7f8edc25225eb4cb63f96b4e6d9b8284
+size 1495095008

llava-phi-2-mmproj.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:03b4efa2bafe36055a45800ba2634d3ab13670c7bc99560cd2750c5ec32ef41d
+size 600829120

llava-phi-2.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb916f0fe3a41c79a629b5927fd6d690a303ae641463391780d6d46b3358803
+size 1737636448

phi-2_Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:324356668fa5ba9f4135de348447bb2bbe2467eaa1b8fcfb53719de62fbd2499
+size 1789239136

tinyllama-1.1b-chat_Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9fecc3b3cd76bba89d504f29b616eedf7da85b96540e490ca5824d3f7d2776a0
+size 668788096