Instructions to use mlx-community/Trinity-Large-Preview-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Trinity-Large-Preview-8bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Trinity-Large-Preview-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use mlx-community/Trinity-Large-Preview-8bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mlx-community/Trinity-Large-Preview-8bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/Trinity-Large-Preview-8bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("mlx-community/Trinity-Large-Preview-8bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/Trinity-Large-Preview-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/Trinity-Large-Preview-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Trinity-Large-Preview-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/Trinity-Large-Preview-8bit

SGLang

How to use mlx-community/Trinity-Large-Preview-8bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mlx-community/Trinity-Large-Preview-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Trinity-Large-Preview-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mlx-community/Trinity-Large-Preview-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Trinity-Large-Preview-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Pi new

How to use mlx-community/Trinity-Large-Preview-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Trinity-Large-Preview-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/Trinity-Large-Preview-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Trinity-Large-Preview-8bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Trinity-Large-Preview-8bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mlx-community/Trinity-Large-Preview-8bit

Run Hermes

hermes

MLX LM

How to use mlx-community/Trinity-Large-Preview-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Trinity-Large-Preview-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Trinity-Large-Preview-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Trinity-Large-Preview-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/Trinity-Large-Preview-8bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/Trinity-Large-Preview-8bit
```

bibproj commited on Feb 10

Commit

cddb364

verified ·

1 Parent(s): 7d16f96

Upload

Browse files

Files changed (20) hide show

model-00001-of-00082.safetensors +3 -0
model-00002-of-00082.safetensors +3 -0
model-00003-of-00082.safetensors +3 -0
model-00004-of-00082.safetensors +3 -0
model-00005-of-00082.safetensors +3 -0
model-00006-of-00082.safetensors +3 -0
model-00007-of-00082.safetensors +3 -0
model-00008-of-00082.safetensors +3 -0
model-00009-of-00082.safetensors +3 -0
model-00010-of-00082.safetensors +3 -0
model-00011-of-00082.safetensors +3 -0
model-00012-of-00082.safetensors +3 -0
model-00013-of-00082.safetensors +3 -0
model-00014-of-00082.safetensors +3 -0
model-00015-of-00082.safetensors +3 -0
model-00016-of-00082.safetensors +3 -0
model-00017-of-00082.safetensors +3 -0
model-00018-of-00082.safetensors +3 -0
model-00019-of-00082.safetensors +3 -0
model-00020-of-00082.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:d44edf9e4ff91215f1c5cc136cf8e4b4aae8e21aef0e3ecffc6ff1c0f9ce04d4
+size 4411223085

+version https://git-lfs.github.com/spec/v1
+oid sha256:b635a8a11f9cb4f2acc0de1cfb9383ee3c700a148a810178f17a18824ea22d85
+size 5231621678

+version https://git-lfs.github.com/spec/v1
+oid sha256:539d63e764341aeae1d693de01a50a81bc9024fd1bdaad0e50ea328551543f95
+size 5133828858

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a4b63b90b556862661a403bf9a7c66f52e8a0347a5e414d55df2dbcb1b8ea2
+size 5231621790

+version https://git-lfs.github.com/spec/v1
+oid sha256:26215f6cd47ef28645b7cb491fc01a6fe6f550f4c210fe33c93e1ee839855ec4
+size 5231621672

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6e5d61f000a6889e682d3cc5cbcf1ffc8583b7840efb304c55210b966aca1d
+size 5133828856

+version https://git-lfs.github.com/spec/v1
+oid sha256:33e87f4698cd64b31d07822cf836215af43c2e1454bde70ae6a75ebf15646c75
+size 5231621814

+version https://git-lfs.github.com/spec/v1
+oid sha256:693b61e87301d02532baa214601295161d86a402d9a470163511e17517a3b56f
+size 5231621748

+version https://git-lfs.github.com/spec/v1
+oid sha256:6aab673e7fd2f3bb8dd0f09339324e70883010362553d46774cdd06f8a38e93e
+size 5133828872

+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfea391f811ac522737e6a9cdba4e2c6431b1aac0f9406c20f2ec1bdd80e379
+size 5231621780

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

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

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

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9314e5c98d500601a11e0bf6b664cbee56dc16557f72df9960b90ec2dd039cdc
+size 5231621728

+version https://git-lfs.github.com/spec/v1
+oid sha256:11685deb71a5b0e2b208efdb9ea99d0e8f0a43117192fa1bd51e4ea663dcdd65
+size 5231621830

+version https://git-lfs.github.com/spec/v1
+oid sha256:dea622aa4b03f6c0cb4ca8c400736b21e1227a07e3e58ed91b9d9a6a54fbb8c1
+size 5231621738

+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc28fa0d326b183ad8f515c83e7bd22239402d1dc461adf9ec9c1c0bec8be18
+size 5133828862

+version https://git-lfs.github.com/spec/v1
+oid sha256:b683c84e4d88f5b45879bd41b07a4869b7032363c5beb3421504ee7ffbcc574a
+size 5231621694

+version https://git-lfs.github.com/spec/v1
+oid sha256:590050e213d7fcdea52d6768a82b81dcb0ac03a0edaecbb364080c482b4e4b3c
+size 5231621710