161 lines
3.2 KiB
JSON
161 lines
3.2 KiB
JSON
{
|
|
"architectures": [
|
|
"SmolLM3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 128012,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"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",
|
|
"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": 65536,
|
|
"max_window_layers": 28,
|
|
"mlp_bias": false,
|
|
"model_type": "smollm3",
|
|
"no_rope_layer_interval": 4,
|
|
"no_rope_layers": [
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
1,
|
|
1,
|
|
1,
|
|
0
|
|
],
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 128004,
|
|
"pretraining_tp": 2,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"format": "nvfp4-pack-quantized",
|
|
"input_activations": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": "local",
|
|
"group_size": 16,
|
|
"num_bits": 4,
|
|
"observer": "static_minmax",
|
|
"observer_kwargs": {},
|
|
"scale_dtype": "torch.float8_e4m3fn",
|
|
"strategy": "tensor_group",
|
|
"symmetric": true,
|
|
"type": "float",
|
|
"zp_dtype": null
|
|
},
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": false,
|
|
"group_size": 16,
|
|
"num_bits": 4,
|
|
"observer": "memoryless_minmax",
|
|
"observer_kwargs": {},
|
|
"scale_dtype": "torch.float8_e4m3fn",
|
|
"strategy": "tensor_group",
|
|
"symmetric": true,
|
|
"type": "float",
|
|
"zp_dtype": null
|
|
}
|
|
}
|
|
},
|
|
"format": "nvfp4-pack-quantized",
|
|
"global_compression_ratio": null,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed",
|
|
"sparsity_config": {},
|
|
"transform_config": {},
|
|
"version": "0.17.1"
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_parameters": {
|
|
"rope_theta": 5000000.0,
|
|
"rope_type": "default"
|
|
},
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "5.10.1",
|
|
"use_cache": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 128256
|
|
} |