LFM3-1.7B-Web / config.json
daveycodez's picture
Block-32 GPTQ with a 48k vocabulary (900 MB of weights)
2395323 verified
Raw History Blame Contribute Delete
1.54 kB
{
"architectures": [
"Lfm3ForCausalLM"
],
"bos_token_id": 49013,
"conv_L_cache": 7,
"conv_bias": false,
"dtype": "bfloat16",
"eos_token_id": 49019,
"head_dim": 128,
"hidden_size": 2048,
"intermediate_size": 7680,
"layer_types": [
"conv",
"conv",
"full_attention",
"conv",
"sliding_attention",
"conv",
"full_attention",
"conv",
"sliding_attention",
"conv",
"full_attention",
"conv",
"sliding_attention",
"conv",
"full_attention",
"conv",
"sliding_attention",
"conv",
"full_attention",
"conv",
"sliding_attention",
"conv",
"full_attention",
"conv"
],
"max_position_embeddings": 262144,
"model_type": "lfm3",
"norm_eps": 1e-05,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 4,
"pad_token_id": 49012,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.5,
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000,
"rope_type": "default"
}
},
"sliding_window": 256,
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"use_cache": true,
"use_sandwich_norm": true,
"vocab_size": 49152,
"transformers.js_config": {
"use_external_data_format": {
"model_fp16.onnx": 2,
"model_q4.onnx": 1,
"model_q4f16.onnx": 1,
"model_quantized.onnx": 2
},
"kv_cache_dtype": {
"fp16": "float16",
"q4f16": "float16"
}
}
}