Hugging Face's logo

QuantTrio
/
GLM-4.5-Air-GPTQ-Int4-Int8Mix

Text Generation
Transformers
Safetensors
glm4_moe
AWQ
FP16Mix
quantization fix
vLLM
conversational
4-bit precision
gptq_marlin
Model card Files Community
GLM-4.5-Air-GPTQ-Int4-Int8Mix
File size: 1,441 Bytes 
b513149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
 
{
  "name_or_path": "tclf90/GLM-4.5-Air-GPTQ-Int4-Int8Mix",
  "architectures": [
    "Glm4MoeForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "pad_token_id": 151329,
  "eos_token_id": [
    151329,
    151336,
    151338
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "partial_rotary_factor": 0.5,
  "initializer_range": 0.02,
  "intermediate_size": 11264,
  "max_position_embeddings": 131072,
  "model_type": "glm4_moe",
  "moe_intermediate_size": 1408,
  "norm_topk_prob": true,
  "num_attention_heads": 96,
  "n_group": 1,
  "topk_group": 1,
  "n_routed_experts": 128,
  "n_shared_experts": 1,
  "routed_scaling_factor": 1.0,
  "num_experts_per_tok": 8,
  "first_k_dense_replace": 1,
  "num_hidden_layers": 46,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "num_nextn_predict_layers": 1,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.54.0",
  "use_cache": true,
  "use_qk_norm": false,
  "vocab_size": 151552,
  "quantization_config": {
    "quant_method": "gptq_marlin",
    "bits": 4,
    "group_size": 128,
    "sym": true,
    "desc_act": false,
    "dynamic": {
      "-:model.embed_tokens.weight": {},
      "-:.*shared_experts": {},
      "-:.*shared_head": {},
      "-:lm_head.weight": {},
      "+:model[.]layers[.]([0-4]|4[4-6])[.].*": {
        "bits": 8
      }
    }
  }
}