Instructions to use mlx-community/plamo-2-translate-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/plamo-2-translate-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/plamo-2-translate-bf16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mlx-community/plamo-2-translate-bf16", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlx-community/plamo-2-translate-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/plamo-2-translate-bf16"
# 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/plamo-2-translate-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/plamo-2-translate-bf16

SGLang

How to use mlx-community/plamo-2-translate-bf16 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/plamo-2-translate-bf16" \
    --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/plamo-2-translate-bf16",
		"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/plamo-2-translate-bf16" \
        --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/plamo-2-translate-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlx-community/plamo-2-translate-bf16 with Docker Model Runner:
```
docker model run hf.co/mlx-community/plamo-2-translate-bf16
```

plamo-2-translate-bf16 / config.json

mitmul

Add files using upload-large-folder tool

3057ac1 verified over 1 year ago

Raw

History Blame Contribute Delete

1.28 kB

	{
	"architectures": [
	"Plamo2ForCausalLM"
	],
	"attention_window_size": 32768,
	"auto_map": {
	"AutoConfig": "modeling_plamo.Plamo2Config",
	"AutoModelForCausalLM": "modeling_plamo.Plamo2ForCausalLM"
	},
	"bos_token_id": 1,
	"eos_token_id": 1,
	"eval_attention_n_bit": null,
	"eval_mlp_n_bit": null,
	"fp8_accum_dtype": "bfloat16",
	"full_attention_idx": [],
	"hidden_size": 4096,
	"hidden_size_per_head": 128,
	"image_feature_size": null,
	"image_proj_type": "linear",
	"image_token_id": null,
	"intermediate_size": 16384,
	"linear_type": "normal",
	"mamba_chunk_size": 256,
	"mamba_d_conv": 4,
	"mamba_d_state": 64,
	"mamba_enabled": true,
	"mamba_num_heads": 64,
	"mamba_step": 2,
	"max_position_embeddings": 10485760,
	"model_type": "plamo2",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"pad_token_id": 3,
	"rms_norm_eps": 1e-06,
	"rope_local_theta": 1000000.0,
	"rope_theta": 1000000.0,
	"sliding_window": 32768,
	"tie_word_embeddings": false,
	"tokenizer_class": "Plamo2Tokenizer",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.46.2",
	"use_cache": false,
	"vocab_size": 100032
	}