Instructions to use amd/Instella-MoE-16B-A3B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Instella-MoE-16B-A3B-Base with Transformers:

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

pipe = pipeline("text-generation", model="amd/Instella-MoE-16B-A3B-Base", 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("amd/Instella-MoE-16B-A3B-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/Instella-MoE-16B-A3B-Base", trust_remote_code=True, device_map="auto")
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 Settings

vLLM

How to use amd/Instella-MoE-16B-A3B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Instella-MoE-16B-A3B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Instella-MoE-16B-A3B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Instella-MoE-16B-A3B-Base

SGLang

How to use amd/Instella-MoE-16B-A3B-Base 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 "amd/Instella-MoE-16B-A3B-Base" \
    --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": "amd/Instella-MoE-16B-A3B-Base",
		"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 "amd/Instella-MoE-16B-A3B-Base" \
        --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": "amd/Instella-MoE-16B-A3B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/Instella-MoE-16B-A3B-Base with Docker Model Runner:
```
docker model run hf.co/amd/Instella-MoE-16B-A3B-Base
```

Instella-MoE-16B-A3B-Base / config.json

Prakamya

Release Instella-MoE-16B-A3B-Base

1ddfce9 verified 8 days ago

Raw

History Blame Contribute Delete

1.69 kB

	{
	"architectures": [
	"InstellaMoEForCausalLM"
	],
	"attention_bias": false,
	"farskip": true,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_instella_moe.InstellaMoEConfig",
	"AutoModel": "modeling_instella_moe.InstellaMoEModel",
	"AutoModelForCausalLM": "modeling_instella_moe.InstellaMoEForCausalLM"
	},
	"aux_loss_alpha": 0.001,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"ep_size": 1,
	"first_k_dense_replace": 1,
	"gated_attention": true,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 10944,
	"kv_lora_rank": 512,
	"qk_layernorm": true,
	"max_position_embeddings": 65536,
	"model_type": "deepseek_v3",
	"moe_intermediate_size": 1408,
	"moe_layer_freq": 1,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"norm_topk_prob": true,
	"num_attention_heads": 16,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"num_nextn_predict_layers": 1,
	"q_lora_rank": null,
	"pretraining_tp": 1,
	"qk_head_dim": 128,
	"qk_nope_head_dim": 96,
	"qk_rope_head_dim": 32,
	"rope_interleave": true,
	"rms_norm_eps": 1e-06,
	"rope_scaling": {
	"beta_fast": 32,
	"beta_slow": 1,
	"factor": 40,
	"mscale": 1.0,
	"mscale_all_dim": 1.0,
	"original_max_position_embeddings": 4096,
	"type": "yarn"
	},
	"rope_theta": 8000000,
	"routed_scaling_factor": 2.5,
	"scoring_func": "sigmoid",
	"seq_aux": true,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.57.1",
	"use_cache": true,
	"v_head_dim": 128,
	"vocab_size": 128896
	}