Hugging Face's logo

samairtimer
/
MobileLLM-R1-360M-4bit

Text Generation
MLX
Safetensors
PyTorch
English
llama4_text
facebook
meta
mobilellm
conversational
4-bit precision
Model card Files
xet
Community
MobileLLM-R1-360M-4bit
File size: 2,257 Bytes 
9094aaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "architectures": [
        "Llama4ForCausalLM"
    ],
    "attention_bias": false,
    "attention_chunk_size": 32768,
    "attention_dropout": 0.0,
    "attn_scale": 0.1,
    "attn_temperature_tuning": false,
    "bos_token_id": 128000,
    "eos_token_id": [
        128001,
        128008,
        128009
    ],
    "floor_scale": 8192,
    "for_llm_compressor": false,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "interleave_moe_layer_step": 0,
    "intermediate_size": 8192,
    "intermediate_size_mlp": 4096,
    "layer_types": [
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention"
    ],
    "max_position_embeddings": 32768,
    "model_type": "llama4_text",
    "moe_layers": [],
    "no_rope_layers": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "num_attention_heads": 16,
    "num_experts_per_tok": 0,
    "num_hidden_layers": 15,
    "num_key_value_heads": 4,
    "num_local_experts": 0,
    "output_router_logits": false,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 8000000.0,
    "router_aux_loss_coef": 0.001,
    "router_jitter_noise": 0.0,
    "tie_word_embeddings": true,
    "torch_dtype": "float32",
    "transformers_version": "4.55.0",
    "use_cache": true,
    "use_qk_norm": true,
    "vocab_size": 128256
}