Instructions to use Diffuspace/Clover-35B-A3B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Diffuspace/Clover-35B-A3B-Preview with Transformers:

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

pipe = pipeline("text-generation", model="Diffuspace/Clover-35B-A3B-Preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Diffuspace/Clover-35B-A3B-Preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Diffuspace/Clover-35B-A3B-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Diffuspace/Clover-35B-A3B-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Diffuspace/Clover-35B-A3B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Diffuspace/Clover-35B-A3B-Preview

SGLang

How to use Diffuspace/Clover-35B-A3B-Preview 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 "Diffuspace/Clover-35B-A3B-Preview" \
    --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": "Diffuspace/Clover-35B-A3B-Preview",
		"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 "Diffuspace/Clover-35B-A3B-Preview" \
        --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": "Diffuspace/Clover-35B-A3B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Diffuspace/Clover-35B-A3B-Preview with Docker Model Runner:
```
docker model run hf.co/Diffuspace/Clover-35B-A3B-Preview
```

Clover-35B-A3B-Preview / config.json

Sansa

ZiruiWu

Add Clover-35B-A3B-Preview release

4b0402b about 19 hours ago

Raw History Blame Contribute Delete

2.58 kB

{
  "architectures": [
    "CloverMoeModelLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_clover_moe.CloverMoeConfig",
    "AutoModel": "modeling_clover_moe.CloverMoeModel",
    "AutoModelForCausalLM": "modeling_clover_moe.CloverMoeModelLM"
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "block_size": 32,
  "bos_token_id": 248044,
  "dtype": "bfloat16",
  "eos_token_id": 248044,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 16,
  "linear_num_value_heads": 32,
  "linear_value_head_dim": 128,
  "mamba_ssm_dtype": "float32",
  "mask_token_id": 151669,
  "max_position_embeddings": 131072,
  "model_type": "clover_moe",
  "moe_block_coreset_enabled": true,
  "moe_block_coreset_top_p": 0.9,
  "moe_intermediate_size": 512,
  "num_attention_heads": 16,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 40,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "pad_token_id": null,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "shared_expert_intermediate_size": 512,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 248320,
  "transformers_version": "5.19.0",
  "num_shared_experts": 1,
  "attention_backend": "sdpa",
  "denoising_config": {
    "algorithm": "low_confidence",
    "threshold": 0.95
  }
}

	{
	"architectures": [
	"CloverMoeModelLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_clover_moe.CloverMoeConfig",
	"AutoModel": "modeling_clover_moe.CloverMoeModel",
	"AutoModelForCausalLM": "modeling_clover_moe.CloverMoeModelLM"
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"block_size": 32,
	"bos_token_id": 248044,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"mask_token_id": 151669,
	"max_position_embeddings": 131072,
	"model_type": "clover_moe",
	"moe_block_coreset_enabled": true,
	"moe_block_coreset_top_p": 0.9,
	"moe_intermediate_size": 512,
	"num_attention_heads": 16,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"output_router_logits": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"shared_expert_intermediate_size": 512,
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 248320,
	"transformers_version": "5.19.0",
	"num_shared_experts": 1,
	"attention_backend": "sdpa",
	"denoising_config": {
	"algorithm": "low_confidence",
	"threshold": 0.95
	}
	}