113 lines
3.0 KiB
JSON
113 lines
3.0 KiB
JSON
|
{
|
||
|
|
"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": 3,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 7168,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 18432,
|
||
|
|
"kv_lora_rank": 512,
|
||
|
|
"max_position_embeddings": 163840,
|
||
|
|
"model_type": "deepseek_v3",
|
||
|
|
"moe_intermediate_size": 2048,
|
||
|
|
"moe_layer_freq": 1,
|
||
|
|
"n_group": 8,
|
||
|
|
"n_routed_experts": 256,
|
||
|
|
"n_shared_experts": 1,
|
||
|
|
"norm_topk_prob": true,
|
||
|
|
"num_attention_heads": 128,
|
||
|
|
"num_experts_per_tok": 8,
|
||
|
|
"num_hidden_layers": 61,
|
||
|
|
"num_key_value_heads": 128,
|
||
|
|
"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_scaling": {
|
||
|
|
"beta_fast": 32,
|
||
|
|
"beta_slow": 1,
|
||
|
|
"factor": 40,
|
||
|
|
"mscale": 1.0,
|
||
|
|
"mscale_all_dim": 1.0,
|
||
|
|
"original_max_position_embeddings": 4096,
|
||
|
|
"type": "yarn"
|
||
|
|
},
|
||
|
|
"rope_theta": 10000,
|
||
|
|
"routed_scaling_factor": 2.5,
|
||
|
|
"scoring_func": "sigmoid",
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"topk_group": 4,
|
||
|
|
"topk_method": "noaux_tc",
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.46.3",
|
||
|
|
"use_cache": true,
|
||
|
|
"v_head_dim": 128,
|
||
|
|
"vocab_size": 129280,
|
||
|
|
"quantization_config": {
|
||
|
|
"config_groups": {
|
||
|
|
"group_0": {
|
||
|
|
"input_activations": {
|
||
|
|
"block_structure": null,
|
||
|
|
"dynamic": true,
|
||
|
|
"group_size": null,
|
||
|
|
"num_bits": 8,
|
||
|
|
"observer": "memoryless",
|
||
|
|
"observer_kwargs": {},
|
||
|
|
"strategy": "token",
|
||
|
|
"symmetric": true,
|
||
|
|
"type": "int"
|
||
|
|
},
|
||
|
|
"output_activations": null,
|
||
|
|
"targets": [
|
||
|
|
"Linear"
|
||
|
|
],
|
||
|
|
"weights": {
|
||
|
|
"block_structure": null,
|
||
|
|
"dynamic": false,
|
||
|
|
"group_size": null,
|
||
|
|
"num_bits": 8,
|
||
|
|
"observer": "minmax",
|
||
|
|
"observer_kwargs": {},
|
||
|
|
"strategy": "channel",
|
||
|
|
"symmetric": true,
|
||
|
|
"type": "int"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"format": "int-quantized",
|
||
|
|
"global_compression_ratio": 1.0,
|
||
|
|
"ignore": [
|
||
|
|
"re:.*embed_tokens.*",
|
||
|
|
"re:.*input_layernorm.*",
|
||
|
|
"re:.*post_attention_layernorm.*",
|
||
|
|
"re:.*kv_a_layernorm.*",
|
||
|
|
"re:.*q_a_layernorm.*",
|
||
|
|
"re:.*eh_proj.*",
|
||
|
|
"re:.*enorm.*",
|
||
|
|
"re:.*hnorm.*",
|
||
|
|
"re:model.layers.\\d+.mlp.gate_proj.*",
|
||
|
|
"re:model.layers.\\d+.mlp.up_proj.*",
|
||
|
|
"re:model.layers.\\d+.mlp.down_proj.*",
|
||
|
|
"re:model.layers.\\d+.mlp.gate\\..*",
|
||
|
|
"re:model.norm.*",
|
||
|
|
"re:model.layers.\\d+.shared_head.norm.*",
|
||
|
|
"re:.*lm_head.*",
|
||
|
|
"re:model.layers.\\d+.shared_head.head.*"
|
||
|
|
],
|
||
|
|
"kv_cache_scheme": null,
|
||
|
|
"quant_method": "compressed-tensors",
|
||
|
|
"quantization_status": "frozen"
|
||
|
|
}
|
||
|
|
}
|