8bit-epoch-10 / config.json
Sathvik265's picture
Upload FP8 base model weights
f849f5d verified
{
"_attn_implementation_autoset": true,
"architectures": [
"Llama4ForCausalLM"
],
"attention_bias": false,
"attention_chunk_size": 8192,
"attention_dropout": 0.0,
"attn_scale": 0.1,
"attn_temperature_tuning": true,
"bos_token_id": 200000,
"dtype": "bfloat16",
"eos_token_id": [
200001,
200007,
200008
],
"floor_scale": 8192,
"for_llm_compressor": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"interleave_moe_layer_step": 1,
"intermediate_size": 8192,
"intermediate_size_mlp": 16384,
"layer_types": [
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention",
"chunked_attention",
"chunked_attention",
"chunked_attention",
"full_attention"
],
"max_position_embeddings": 10485760,
"model_type": "llama4_text",
"moe_layers": [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
26,
27,
28,
29,
30,
31,
32,
33,
34,
35,
36,
37,
38,
39,
40,
41,
42,
43,
44,
45,
46,
47
],
"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,
1,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
0
],
"num_attention_heads": 40,
"num_experts_per_tok": 1,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"num_local_experts": 16,
"output_router_logits": false,
"pad_token_id": 200018,
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"input_activations": {
"dynamic": true,
"num_bits": 8,
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"targets": [
"Linear"
],
"weights": {
"dynamic": false,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"ignore": [
"lm_head"
],
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.13.0"
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 16.0,
"high_freq_factor": 1.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"tie_word_embeddings": false,
"transformers_version": "4.57.2",
"use_cache": true,
"use_qk_norm": true,
"vocab_size": 202048
}