TreeSoft/Prism-1-Mini
219
1{
2 "architectures": [
3 "Qwen3_5ForCausalLM"
4 ],
5 "attention_bias": false,
6 "attention_dropout": 0.0,
7 "attn_output_gate": true,
8 "bos_token_id": null,
9 "dtype": "bfloat16",
10 "eos_token_id": 248044,
11 "full_attention_interval": 4,
12 "head_dim": 256,
13 "hidden_act": "silu",
14 "hidden_size": 1024,
15 "initializer_range": 0.02,
16 "intermediate_size": 3584,
17 "layer_types": [
18 "linear_attention",
19 "linear_attention",
20 "linear_attention",
21 "full_attention",
22 "linear_attention",
23 "linear_attention",
24 "linear_attention",
25 "full_attention",
26 "linear_attention",
27 "linear_attention",
28 "linear_attention",
29 "full_attention",
30 "linear_attention",
31 "linear_attention",
32 "linear_attention",
33 "full_attention",
34 "linear_attention",
35 "linear_attention",
36 "linear_attention",
37 "full_attention",
38 "linear_attention",
39 "linear_attention",
40 "linear_attention",
41 "full_attention"
42 ],
43 "linear_conv_kernel_dim": 4,
44 "linear_key_head_dim": 128,
45 "linear_num_key_heads": 16,
46 "linear_num_value_heads": 16,
47 "linear_value_head_dim": 128,
48 "mamba_ssm_dtype": "float32",
49 "max_position_embeddings": 262144,
50 "mlp_only_layers": [],
51 "model_type": "qwen3_5_text",
52 "mtp_num_hidden_layers": 1,
53 "mtp_use_dedicated_embeddings": false,
54 "num_attention_heads": 8,
55 "num_hidden_layers": 24,
56 "num_key_value_heads": 2,
57 "pad_token_id": null,
58 "partial_rotary_factor": 0.25,
59 "rms_norm_eps": 1e-06,
60 "rope_parameters": {
61 "mrope_interleaved": true,
62 "mrope_section": [
63 11,
64 11,
65 10
66 ],
67 "partial_rotary_factor": 0.25,
68 "rope_theta": 10000000,
69 "rope_type": "default"
70 },
71 "tie_word_embeddings": true,
72 "transformers_version": "5.13.0",
73 "use_cache": true,
74 "vocab_size": 248320
75}
76 