Instructions to use MarsupialAI/Llama3_GGUF_Quant_Testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarsupialAI/Llama3_GGUF_Quant_Testing with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MarsupialAI/Llama3_GGUF_Quant_Testing",
	filename="L3-f16-Q4km.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 MarsupialAI/Llama3_GGUF_Quant_Testing 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 MarsupialAI/Llama3_GGUF_Quant_Testing:F16
# Run inference directly in the terminal:
llama cli -hf MarsupialAI/Llama3_GGUF_Quant_Testing:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MarsupialAI/Llama3_GGUF_Quant_Testing:F16
# Run inference directly in the terminal:
llama cli -hf MarsupialAI/Llama3_GGUF_Quant_Testing:F16

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 MarsupialAI/Llama3_GGUF_Quant_Testing:F16
# Run inference directly in the terminal:
./llama-cli -hf MarsupialAI/Llama3_GGUF_Quant_Testing:F16

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 MarsupialAI/Llama3_GGUF_Quant_Testing:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MarsupialAI/Llama3_GGUF_Quant_Testing:F16

Use Docker

docker model run hf.co/MarsupialAI/Llama3_GGUF_Quant_Testing:F16

LM Studio
Jan
Ollama
How to use MarsupialAI/Llama3_GGUF_Quant_Testing with Ollama:
```
ollama run hf.co/MarsupialAI/Llama3_GGUF_Quant_Testing:F16
```

Unsloth Studio

How to use MarsupialAI/Llama3_GGUF_Quant_Testing 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 MarsupialAI/Llama3_GGUF_Quant_Testing 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 MarsupialAI/Llama3_GGUF_Quant_Testing to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MarsupialAI/Llama3_GGUF_Quant_Testing to start chatting

Atomic Chat new
Docker Model Runner
How to use MarsupialAI/Llama3_GGUF_Quant_Testing with Docker Model Runner:
```
docker model run hf.co/MarsupialAI/Llama3_GGUF_Quant_Testing:F16
```

Lemonade

How to use MarsupialAI/Llama3_GGUF_Quant_Testing with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MarsupialAI/Llama3_GGUF_Quant_Testing:F16

Run and chat with the model

lemonade run user.Llama3_GGUF_Quant_Testing-F16

List all available models

lemonade list

MarsupialAI commited on May 11, 2024

Commit

828da3b

verified ·

1 Parent(s): afcbb60

Upload 6 files

Browse files

Files changed (7) hide show

.gitattributes +6 -0
imat_testing/L38ablit_fp32_Q4.gguf +3 -0
imat_testing/L38ablit_fp32_Q4ks.gguf +3 -0
imat_testing/L38ablit_fp32_Q8.gguf +3 -0
imat_testing/L38ablit_fp32_imat32_Q4ks.gguf +3 -0
imat_testing/L38ablit_fp32_imat4_Q4ks.gguf +3 -0
imat_testing/L38ablit_fp32_imat8_Q4ks.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -45,3 +45,9 @@ imat_testing/L38ablit_fp16_imat8_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
 imat_testing/L38ablit_fp16_Q4.gguf filter=lfs diff=lfs merge=lfs -text
 imat_testing/L38ablit_fp16_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
 imat_testing/L38ablit_fp16_Q8.gguf filter=lfs diff=lfs merge=lfs -text

 imat_testing/L38ablit_fp16_Q4.gguf filter=lfs diff=lfs merge=lfs -text
 imat_testing/L38ablit_fp16_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
 imat_testing/L38ablit_fp16_Q8.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_imat32_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_imat4_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_imat8_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_Q4.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_Q4ks.gguf filter=lfs diff=lfs merge=lfs -text
+imat_testing/L38ablit_fp32_Q8.gguf filter=lfs diff=lfs merge=lfs -text

imat_testing/L38ablit_fp32_Q4.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:86b55a4d4db9916f96a059e0ade4a5092c006f645eabdf7edf5185f7830d74b3
+size 4661211392

imat_testing/L38ablit_fp32_Q4ks.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:25a1578be4cccee6303886e3214dc9c1d2400d2ed808dd339fafda4fbceb9af7
+size 4692668672

imat_testing/L38ablit_fp32_Q8.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:651c1cd6882b1e4b314083da4029729a40689ced47b9bb0ce13fc27c2d8ab169
+size 8540770560

imat_testing/L38ablit_fp32_imat32_Q4ks.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed795f9caacc839f9205bc187d7762647738cf8c3cf19e9cc2d619fa51c56c75
+size 4692668896

imat_testing/L38ablit_fp32_imat4_Q4ks.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fbaa61943383d90b4b4bab6dd92d8c51949020fd5a71eb981d991f759508a60f
+size 4692668896

imat_testing/L38ablit_fp32_imat8_Q4ks.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:86c1e8cc535fb47ef9537845ed5e01295142de69237418a68717ba05cf02d2ab
+size 4692668896