Instructions to use neka-nat/llm-quantized-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neka-nat/llm-quantized-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="neka-nat/llm-quantized-models",
	filename="Llama-3-Swallow-70B-Instruct-v0.1-Q3_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use neka-nat/llm-quantized-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neka-nat/llm-quantized-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf neka-nat/llm-quantized-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 neka-nat/llm-quantized-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf neka-nat/llm-quantized-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 neka-nat/llm-quantized-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf neka-nat/llm-quantized-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 neka-nat/llm-quantized-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neka-nat/llm-quantized-models:Q4_K_M

Use Docker

docker model run hf.co/neka-nat/llm-quantized-models:Q4_K_M

LM Studio
Jan
Ollama
How to use neka-nat/llm-quantized-models with Ollama:
```
ollama run hf.co/neka-nat/llm-quantized-models:Q4_K_M
```

Unsloth Studio new

How to use neka-nat/llm-quantized-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 neka-nat/llm-quantized-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 neka-nat/llm-quantized-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neka-nat/llm-quantized-models to start chatting

Docker Model Runner
How to use neka-nat/llm-quantized-models with Docker Model Runner:
```
docker model run hf.co/neka-nat/llm-quantized-models:Q4_K_M
```

Lemonade

How to use neka-nat/llm-quantized-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neka-nat/llm-quantized-models:Q4_K_M

Run and chat with the model

lemonade run user.llm-quantized-models-Q4_K_M

List all available models

lemonade list

neka-nat commited on Jul 14, 2024

Commit

49cc177

verified ·

1 Parent(s): 33d1ed8

Upload Llama-3-Swallow-70B-Instruct-v0.1-Q3_K_M.gguf

Browse files

Files changed (2) hide show

.gitattributes +1 -0
Llama-3-Swallow-70B-Instruct-v0.1-Q3_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -42,3 +42,4 @@ llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v
 Phi-3-medium-4k-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 calm3-22b-chat-23B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3-Swallow-70B-Instruct-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

 Phi-3-medium-4k-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 calm3-22b-chat-23B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3-Swallow-70B-Instruct-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-Swallow-70B-Instruct-v0.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-Swallow-70B-Instruct-v0.1-Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b03583916b12d3b3867e593b431d7a275eb886ab5e39230f63694b454ea982b
+size 34267493952