Instructions to use hs-hf/madlad400-3b-mt-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hs-hf/madlad400-3b-mt-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hs-hf/madlad400-3b-mt-gguf",
	filename="madlad400-3b-mt-FP16.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 hs-hf/madlad400-3b-mt-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hs-hf/madlad400-3b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf hs-hf/madlad400-3b-mt-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hs-hf/madlad400-3b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf hs-hf/madlad400-3b-mt-gguf: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 hs-hf/madlad400-3b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hs-hf/madlad400-3b-mt-gguf: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 hs-hf/madlad400-3b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hs-hf/madlad400-3b-mt-gguf:Q4_K_M

Use Docker

docker model run hf.co/hs-hf/madlad400-3b-mt-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use hs-hf/madlad400-3b-mt-gguf with Ollama:
```
ollama run hf.co/hs-hf/madlad400-3b-mt-gguf:Q4_K_M
```

Unsloth Studio

How to use hs-hf/madlad400-3b-mt-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 hs-hf/madlad400-3b-mt-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 hs-hf/madlad400-3b-mt-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hs-hf/madlad400-3b-mt-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use hs-hf/madlad400-3b-mt-gguf with Docker Model Runner:
```
docker model run hf.co/hs-hf/madlad400-3b-mt-gguf:Q4_K_M
```

Lemonade

How to use hs-hf/madlad400-3b-mt-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hs-hf/madlad400-3b-mt-gguf:Q4_K_M

Run and chat with the model

lemonade run user.madlad400-3b-mt-gguf-Q4_K_M

List all available models

lemonade list

hs-hf commited on Oct 28, 2024

Commit

a2ebe1a

verified ·

1 Parent(s): a64447f

Converted the google/madlad400-3b-mt model into quantized GGUF format

Browse files

Files changed (8) hide show

.gitattributes +7 -0
madlad400-3b-mt-FP16.gguf +3 -0
madlad400-3b-mt-q4_k_m.gguf +3 -0
madlad400-3b-mt-q4_k_s.gguf +3 -0
madlad400-3b-mt-q5_k_m.gguf +3 -0
madlad400-3b-mt-q5_k_s.gguf +3 -0
madlad400-3b-mt-q6_k.gguf +3 -0
madlad400-3b-mt-q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,10 @@ 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
+madlad400-3b-mt-FP16.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+madlad400-3b-mt-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

madlad400-3b-mt-FP16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e25b7ccbfc5cb2933d0b7b1a2effd0c3248d208a4008e21d907b303f989ca567
+size 5887332128

madlad400-3b-mt-q4_k_m.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4f14073b53bdadfa843cd986dc7e778cff2d65298fdb83b1fb5c6dcd0085d6
+size 1858129696

madlad400-3b-mt-q4_k_s.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4757d2e516c142f9b3dc00fa0306742cef78d7db4a681c10009b75d330550b6f
+size 1733611296

madlad400-3b-mt-q5_k_m.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc566227f92b11752923a6302c8fc3cdfe0b5b07071159d77bfeeebd40db6d4
+size 2129973024

madlad400-3b-mt-q5_k_s.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c69396d00118f49575885854ab564f4b3d0a76440426cb9dfc8615859746bd9
+size 2063126304

madlad400-3b-mt-q6_k.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fc230c7908b76004488d899d433ef3046b868aa5593993b41094b4d795bc42aa
+size 2418806560

madlad400-3b-mt-q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0897265e1d6f171880b618c45aca30b55019ff4a90aba152fbc197c0451771
+size 3130887968