Instructions to use cortexso/tulu3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/tulu3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/tulu3",
	filename="llama-3.1-tulu-3-8b-sft-q2_k.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cortexso/tulu3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/tulu3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/tulu3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/tulu3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/tulu3: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 cortexso/tulu3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/tulu3: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 cortexso/tulu3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/tulu3:Q4_K_M

Use Docker

docker model run hf.co/cortexso/tulu3:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/tulu3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/tulu3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/tulu3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/tulu3:Q4_K_M

Ollama
How to use cortexso/tulu3 with Ollama:
```
ollama run hf.co/cortexso/tulu3:Q4_K_M
```

Unsloth Studio new

How to use cortexso/tulu3 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 cortexso/tulu3 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 cortexso/tulu3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/tulu3 to start chatting

Docker Model Runner
How to use cortexso/tulu3 with Docker Model Runner:
```
docker model run hf.co/cortexso/tulu3:Q4_K_M
```

Lemonade

How to use cortexso/tulu3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/tulu3:Q4_K_M

Run and chat with the model

lemonade run user.tulu3-Q4_K_M

List all available models

lemonade list

jan-hq commited on Feb 26, 2025

Commit

f247d48

verified ·

1 Parent(s): bbf216e

Upload folder using huggingface_hub

Browse files

Files changed (11) hide show

.gitattributes +10 -0
llama-3.1-tulu-3-8b-sft-q2_k.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q3_k_l.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q3_k_m.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q3_k_s.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q4_k_m.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q4_k_s.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q5_k_m.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q5_k_s.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q6_k.gguf +3 -0
llama-3.1-tulu-3-8b-sft-q8_0.gguf +3 -0

@@ -33,3 +33,13 @@ 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
+llama-3.1-tulu-3-8b-sft-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.1-tulu-3-8b-sft-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:d400a36804b891aef71b759ce0d48c13819cfc3761f4665b9199340e9ffdd36d
+size 3179170272

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1a2d0ad6c366fa492b2d2b7c0cf371239aaa5b0ae09270a6acce9722e8eb65
+size 4321998560

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4b450ad22a15b3bf048f2115094bfc9e6643d34181e62c0b147a26f6961ceb
+size 4018960096

+version https://git-lfs.github.com/spec/v1
+oid sha256:c394ecfc2616a8a7becc325986dbd403b50bc70e31db842e18ab6449f166c788
+size 3664541408

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd482aceb53842eeabfd7294e61a7975d56425a866117987431d958caadf8350
+size 4920780768

+version https://git-lfs.github.com/spec/v1
+oid sha256:e08cf870f31a0a4ac8cda786a79088dfda61a88f116b4ef02ce022a58bf66aea
+size 4692715488

+version https://git-lfs.github.com/spec/v1
+oid sha256:eff8fe0029677fb618de95a691d3a1d98157023050e6ccf66cedf6da7b076977
+size 5733038048

+version https://git-lfs.github.com/spec/v1
+oid sha256:20f064619cd1a06f96a8b24832aefa4566a6044e6142f6e383d3274674866c7b
+size 5599344608

+version https://git-lfs.github.com/spec/v1
+oid sha256:19d64d7097d12d569fbd8dcc6d6dc8f57d10d837185d108edb1f0415bcab1539
+size 6596061408

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb64b69bbda9786d3e496e457809a7c91c212ea3df790dd6c42ee09d0b76fd2d
+size 8540841696

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

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

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

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