Hugging Face's logo

jdopensource
/
JoyAI-LLM-Flash-INT4

Text Generation
Transformers
Safetensors
Chinese
English
joyai_llm_flash
conversational
custom_code
compressed-tensors
Model card Files
xet
Community
JoyAI-LLM-Flash-INT4
File size: 2,455 Bytes
f2121c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "architectures": [
        "DeepseekV3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
        "AutoModel": "modeling_deepseek.DeepseekV3Model",
        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
    },
    "bos_token_id": 0,
    "eos_token_id": 1,
    "ep_size": 1,
    "first_k_dense_replace": 1,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 7168,
    "kv_lora_rank": 512,
    "max_position_embeddings": 131072,
    "model_type": "joyai_llm_flash",
    "moe_intermediate_size": 768,
    "moe_layer_freq": 1,
    "n_group": 1,
    "n_routed_experts": 256,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 32,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 40,
    "num_key_value_heads": 32,
    "num_nextn_predict_layers": 1,
    "q_lora_rank": 1536,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "rms_norm_eps": 1e-06,
    "rope_theta": 32000000,
    "routed_scaling_factor": 2.5,
    "scoring_func": "sigmoid",
    "tie_word_embeddings": false,
    "topk_group": 1,
    "topk_method": "noaux_tc",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.44.2",
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 129280,
    "quantization_config": {
        "config_groups": {
            "group_0": {
                "input_activations": null,
                "output_activations": null,
                "targets": [
                    "Linear"
                ],
                "weights": {
                    "actorder": null,
                    "block_structure": null,
                    "dynamic": false,
                    "group_size": 32,
                    "num_bits": 4,
                    "observer": "minmax",
                    "observer_kwargs": {},
                    "strategy": "group",
                    "symmetric": true,
                    "type": "int"
                }
            }
        },
        "format": "pack-quantized",
        "ignore": [
            "lm_head",
            "re:.*self_attn.*",
            "re:.*shared_experts.*",
            "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
        ],
        "kv_cache_scheme": null,
        "quant_method": "compressed-tensors",
        "quantization_status": "compressed"
    }
}