Instructions to use ArunKr/LLM-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArunKr/LLM-Models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ArunKr/LLM-Models",
	filename="Meta-Llama-3-70B_fp16_shards/-00001-of-00006.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 ArunKr/LLM-Models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ArunKr/LLM-Models:Q4_K_M_SHARDS
# Run inference directly in the terminal:
llama-cli -hf ArunKr/LLM-Models:Q4_K_M_SHARDS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ArunKr/LLM-Models:Q4_K_M_SHARDS
# Run inference directly in the terminal:
llama-cli -hf ArunKr/LLM-Models:Q4_K_M_SHARDS

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 ArunKr/LLM-Models:Q4_K_M_SHARDS
# Run inference directly in the terminal:
./llama-cli -hf ArunKr/LLM-Models:Q4_K_M_SHARDS

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 ArunKr/LLM-Models:Q4_K_M_SHARDS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ArunKr/LLM-Models:Q4_K_M_SHARDS

Use Docker

docker model run hf.co/ArunKr/LLM-Models:Q4_K_M_SHARDS

LM Studio
Jan

Ollama

How to use ArunKr/LLM-Models with Ollama:

ollama run hf.co/ArunKr/LLM-Models:Q4_K_M_SHARDS

Unsloth Studio new

How to use ArunKr/LLM-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 ArunKr/LLM-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 ArunKr/LLM-Models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ArunKr/LLM-Models to start chatting

Docker Model Runner
How to use ArunKr/LLM-Models with Docker Model Runner:
```
docker model run hf.co/ArunKr/LLM-Models:Q4_K_M_SHARDS
```

Lemonade

How to use ArunKr/LLM-Models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ArunKr/LLM-Models:Q4_K_M_SHARDS

Run and chat with the model

lemonade run user.LLM-Models-Q4_K_M_SHARDS

List all available models

lemonade list

Arun1982 commited on May 15, 2024

Commit

89e2fdc

verified ·

1 Parent(s): 5903f80

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

Meta-Llama-3-70B_fp16_Q3_K_S.bin +3 -0
run_gguf.sh +3 -1

Meta-Llama-3-70B_fp16_Q3_K_S.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:768c31b519abda73053385e10077da8a2abb1f34a8c1349e29f6754f4ba35d2f
+size 30912050240

run_gguf.sh CHANGED Viewed

@@ -1,3 +1,5 @@
-./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
 #./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
 #./main -m output/converted_f16.bin -p "hi"

+./main -m output/Meta-Llama-3-70B_fp16_Q3_K_S.bin -p "hi"
+#./main -m output/Meta-Llama-3-8B-Instruct_fp16_Q4_K_M.bin -p "hi"
+#./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
 #./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
 #./main -m output/converted_f16.bin -p "hi"