hf-transformers-bot's picture
Update tiny models for Glm5NextForConditionalGeneration
bf73a3e verified
Raw History Blame Contribute Delete
2.5 kB
{
"architectures": [
"Glm5NextForConditionalGeneration"
],
"dtype": "float32",
"image_end_token_id": 6,
"image_start_token_id": 5,
"image_token_id": 7,
"model_type": "glm5_next",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 154820,
"hc_eps": 1e-06,
"hc_mult": 4,
"hc_sinkhorn_iters": 20,
"head_dim": 0,
"hidden_act": "silu",
"hidden_size": 48,
"index_head_dim": 16,
"index_kpool": 3,
"index_kpool_always_select_tail": true,
"index_n_heads": 2,
"index_topk": 48,
"indexer_types": [
"full",
"full"
],
"initializer_range": 0.02,
"intermediate_size": 16,
"kv_lora_rank": 16,
"layer_types": [
"linear_attention",
"indexed_attention"
],
"linear_conv_kernel_dim": 2,
"linear_head_dim": 16,
"linear_lower_bound": -5.0,
"linear_num_heads": 2,
"max_position_embeddings": 512,
"mlp_layer_types": [
"dense",
"sparse"
],
"model_type": "glm5_next_text",
"moe_intermediate_size": 16,
"n_group": 1,
"n_routed_experts": 8,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 2,
"num_experts_per_tok": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"output_router_logits": false,
"pad_token_id": 154820,
"q_lora_rank": 32,
"qk_head_dim": 64,
"qk_nope_head_dim": 64,
"qk_rope_head_dim": 0,
"rms_norm_eps": 1e-05,
"routed_scaling_factor": 2.5,
"router_aux_loss_coef": 0.001,
"swiglu_limit": 10.0,
"tie_word_embeddings": false,
"topk_group": 1,
"use_cache": true,
"v_head_dim": 16,
"vocab_size": 154856
},
"tie_word_embeddings": false,
"transformers_version": "5.19.0.dev0",
"video_end_token_id": 4,
"video_start_token_id": 3,
"video_token_id": 8,
"vision_config": {
"attention_bias": true,
"attention_dropout": 0.0,
"depth": 2,
"hidden_act": "silu",
"hidden_size": 48,
"image_size": 336,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 16,
"model_type": "glm5_next_vision",
"num_heads": 2,
"out_hidden_size": 48,
"patch_size": 14,
"projection_intermediate_size": 144,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "axial"
},
"spatial_merge_size": 1,
"swiglu_limit": 10.0,
"temporal_patch_size": 2
}
}