Instructions to use patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2 with Transformers:

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

pipe = pipeline("text-generation", model="patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2")
model = AutoModelForMultimodalLM.from_pretrained("patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2

SGLang

How to use patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2 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 "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2" \
    --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": "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2",
		"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 "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2" \
        --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": "patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2 with Docker Model Runner:
```
docker model run hf.co/patrickbdevaney/GLM-5.3-Flash-REAP50-NVFP4-v2
```

GLM-5.3-Flash-REAP50-NVFP4-v2 / config.json

patrickbdevaney

Upload folder using huggingface_hub

d432f65 verified 2 months ago

Raw History Blame Contribute Delete

6.97 kB

{
  "architectures": [
    "Glm5NextForConditionalGeneration"
  ],
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "eos_token_id": [
      154820,
      154827,
      154829
    ],
    "first_k_dense_replace": 3,
    "hc_eps": 1e-06,
    "hc_mult": 4,
    "hc_sinkhorn_iters": 20,
    "head_dim": 0,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "index_head_dim": 128,
    "index_kpool": 4,
    "index_kpool_always_select_tail": true,
    "index_kpool_compress": true,
    "index_n_heads": 32,
    "index_topk": 2048,
    "index_share_for_mtp_iteration": true,
    "indexer_rope_interleave": true,
    "indexer_types": [
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full"
    ],
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "kv_lora_rank": 512,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "deepseek_sparse_attention",
      "linear_attention"
    ],
    "linear_attn_config": {
      "num_heads": 64,
      "gate_lower_bound": -5.0,
      "head_dim": 128,
      "short_conv_kernel_size": 4,
      "kda_layers": [
        0,
        1,
        2,
        4,
        5,
        6,
        8,
        9,
        10,
        12,
        13,
        14,
        16,
        17,
        18,
        20,
        21,
        22,
        24,
        25,
        26,
        28,
        29,
        30,
        32,
        33,
        34,
        36,
        37,
        38,
        40,
        41,
        42,
        44
      ],
      "full_attn_layers": [
        3,
        7,
        11,
        15,
        19,
        23,
        27,
        31,
        35,
        39,
        43
      ]
    },
    "max_position_embeddings": 1048576,
    "mhc": true,
    "mla_use_nope": true,
    "mlp_layer_types": [
      "dense",
      "dense",
      "dense",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse"
    ],
    "model_type": "glm5_next_text",
    "moe_intermediate_size": 2048,
    "moe_router_dtype": "float32",
    "n_group": 1,
    "n_routed_experts": 144,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 64,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 45,
    "num_key_value_heads": 64,
    "num_nextn_predict_layers": 1,
    "output_router_logits": false,
    "pad_token_id": 154820,
    "q_lora_rank": 1536,
    "qk_head_dim": 256,
    "qk_nope_head_dim": 256,
    "qk_rope_head_dim": 0,
    "rms_norm_eps": 1e-05,
    "routed_scaling_factor": 2.5,
    "router_aux_loss_coef": 0.001,
    "scoring_func": "sigmoid",
    "swiglu_limit": 10.0,
    "tie_word_embeddings": false,
    "topk_group": 1,
    "topk_method": "noaux_tc",
    "use_cache": true,
    "v_head_dim": 256,
    "vocab_size": 154880,
    "num_local_experts": 144
  },
  "vision_config": {
    "attention_bias": true,
    "attention_dropout": 0.0,
    "depth": 24,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "image_size": 448,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "glm5_next_vision",
    "num_heads": 16,
    "out_hidden_size": 4096,
    "patch_size": 14,
    "projection_intermediate_size": 10240,
    "rms_norm_eps": 1e-05,
    "spatial_merge_size": 2,
    "swiglu_limit": 10.0,
    "temporal_patch_size": 2
  },
  "image_token_id": 154854,
  "video_token_id": 154855,
  "image_start_token_id": 154830,
  "image_end_token_id": 154831,
  "video_start_token_id": 154832,
  "video_end_token_id": 154833,
  "tie_word_embeddings": false,
  "model_type": "glm5_next",
  "transformers_version": "5.16.0",
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "nvfp4-pack-quantized",
    "quantization_status": "compressed",
    "ignore": [
      "re:.*lm_head.*",
      "re:.*embed_tokens.*",
      "re:.*visual.*",
      "re:.*self_attn.*",
      "re:.*indexer.*",
      "re:.*hc_.*",
      "re:.*mapping_proj.*",
      "re:.*mlp\\.gate\\..*",
      "re:.*norm.*"
    ],
    "config_groups": {
      "group_0": {
        "targets": [
          "Linear"
        ],
        "weights": {
          "num_bits": 4,
          "type": "float",
          "symmetric": true,
          "strategy": "tensor_group",
          "group_size": 16,
          "scale_dtype": "float8_e4m3fn",
          "dynamic": false
        },
        "input_activations": null,
        "output_activations": null
      }
    }
  },
  "reap": {
    "ratio": 0.5,
    "experts_kept": 144,
    "experts_original": 288,
    "mtp_preserved": true,
    "mtp_criterion": "weight-norm (no activation saliency)"
  }
}

	{
	"architectures": [
	"Glm5NextForConditionalGeneration"
	],
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"first_k_dense_replace": 3,
	"hc_eps": 1e-06,
	"hc_mult": 4,
	"hc_sinkhorn_iters": 20,
	"head_dim": 0,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"index_head_dim": 128,
	"index_kpool": 4,
	"index_kpool_always_select_tail": true,
	"index_kpool_compress": true,
	"index_n_heads": 32,
	"index_topk": 2048,
	"index_share_for_mtp_iteration": true,
	"indexer_rope_interleave": true,
	"indexer_types": [
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full"
	],
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"kv_lora_rank": 512,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention"
	],
	"linear_attn_config": {
	"num_heads": 64,
	"gate_lower_bound": -5.0,
	"head_dim": 128,
	"short_conv_kernel_size": 4,
	"kda_layers": [
	0,
	1,
	2,
	4,
	5,
	6,
	8,
	9,
	10,
	12,
	13,
	14,
	16,
	17,
	18,
	20,
	21,
	22,
	24,
	25,
	26,
	28,
	29,
	30,
	32,
	33,
	34,
	36,
	37,
	38,
	40,
	41,
	42,
	44
	],
	"full_attn_layers": [
	3,
	7,
	11,
	15,
	19,
	23,
	27,
	31,
	35,
	39,
	43
	]
	},
	"max_position_embeddings": 1048576,
	"mhc": true,
	"mla_use_nope": true,
	"mlp_layer_types": [
	"dense",
	"dense",
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "glm5_next_text",
	"moe_intermediate_size": 2048,
	"moe_router_dtype": "float32",
	"n_group": 1,
	"n_routed_experts": 144,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 45,
	"num_key_value_heads": 64,
	"num_nextn_predict_layers": 1,
	"output_router_logits": false,
	"pad_token_id": 154820,
	"q_lora_rank": 1536,
	"qk_head_dim": 256,
	"qk_nope_head_dim": 256,
	"qk_rope_head_dim": 0,
	"rms_norm_eps": 1e-05,
	"routed_scaling_factor": 2.5,
	"router_aux_loss_coef": 0.001,
	"scoring_func": "sigmoid",
	"swiglu_limit": 10.0,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880,
	"num_local_experts": 144
	},
	"vision_config": {
	"attention_bias": true,
	"attention_dropout": 0.0,
	"depth": 24,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 448,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "glm5_next_vision",
	"num_heads": 16,
	"out_hidden_size": 4096,
	"patch_size": 14,
	"projection_intermediate_size": 10240,
	"rms_norm_eps": 1e-05,
	"spatial_merge_size": 2,
	"swiglu_limit": 10.0,
	"temporal_patch_size": 2
	},
	"image_token_id": 154854,
	"video_token_id": 154855,
	"image_start_token_id": 154830,
	"image_end_token_id": 154831,
	"video_start_token_id": 154832,
	"video_end_token_id": 154833,
	"tie_word_embeddings": false,
	"model_type": "glm5_next",
	"transformers_version": "5.16.0",
	"quantization_config": {
	"quant_method": "compressed-tensors",
	"format": "nvfp4-pack-quantized",
	"quantization_status": "compressed",
	"ignore": [
	"re:.lm_head.",
	"re:.embed_tokens.",
	"re:.visual.",
	"re:.self_attn.",
	"re:.indexer.",
	"re:.hc_.",
	"re:.mapping_proj.",
	"re:.mlp\\.gate\\..",
	"re:.norm."
	],
	"config_groups": {
	"group_0": {
	"targets": [
	"Linear"
	],
	"weights": {
	"num_bits": 4,
	"type": "float",
	"symmetric": true,
	"strategy": "tensor_group",
	"group_size": 16,
	"scale_dtype": "float8_e4m3fn",
	"dynamic": false
	},
	"input_activations": null,
	"output_activations": null
	}
	}
	},
	"reap": {
	"ratio": 0.5,
	"experts_kept": 144,
	"experts_original": 288,
	"mtp_preserved": true,
	"mtp_criterion": "weight-norm (no activation saliency)"
	}
	}