Hugging Face's logo

unsloth
/
granite-4.0-1b-unsloth-bnb-4bit

Text Generation
Transformers
Safetensors
granitemoehybrid
language
unsloth
granite-4.0
conversational
4-bit precision
bitsandbytes
Model card Files
xet
Community
granite-4.0-1b-unsloth-bnb-4bit
File size: 2,870 Bytes 
26c2106
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
 
{
  "architectures": [
    "GraniteMoeHybridForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 0.0078125,
  "bos_token_id": 100257,
  "torch_dtype": "bfloat16",
  "embedding_multiplier": 12,
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "init_method": "mup",
  "initializer_range": 0.1,
  "intermediate_size": 4096,
  "layer_types": [
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention",
    "attention"
  ],
  "logits_scaling": 8,
  "mamba_chunk_size": 256,
  "mamba_conv_bias": true,
  "mamba_d_conv": 4,
  "mamba_d_head": 32,
  "mamba_d_state": 256,
  "mamba_expand": 2,
  "mamba_n_groups": 1,
  "mamba_n_heads": 128,
  "mamba_proj_bias": false,
  "max_position_embeddings": 131072,
  "model_type": "granitemoehybrid",
  "normalization_function": "rmsnorm",
  "num_attention_heads": 16,
  "num_experts_per_tok": 0,
  "num_hidden_layers": 40,
  "num_key_value_heads": 4,
  "num_local_experts": 0,
  "output_router_logits": false,
  "pad_token_id": 100256,
  "position_embedding_type": "rope",
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "embed_tokens",
      "embedding",
      "lm_head",
      "multi_modal_projector",
      "merger",
      "modality_projection",
      "router",
      "visual",
      "vision_tower",
      "mamba",
      "model.layers.0.shared_mlp",
      "model.layers.4.shared_mlp",
      "model.layers.39.shared_mlp",
      "model.layers.2.shared_mlp",
      "model.layers.39.shared_mlp.input_linear"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000000,
  "router_aux_loss_coef": 0.01,
  "shared_intermediate_size": 4096,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "unsloth_fixed": true,
  "use_cache": true,
  "vocab_size": 100352
}