tev1:4b-mxfp8

8,918 3 minutes ago

A 4B decision model from Together AI for fast classification.

tools thinking 0.8b 4b
... /
json
f904f263cd0c · 6.8kB
{
"architectures": [
"Qwen3_5ForCausalLM"
],
"model_type": "qwen3_5",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9216,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 0,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 248320,
"mamba_ssm_dtype": "float32",
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
}
},
"tie_word_embeddings": true,
"transformers_version": "4.57.0.dev0",
"quantization": {
"bits": 8,
"mode": "mxfp8"
},
"quantization_config": {
"ignore": [
"model.language_model.layers.0.linear_attn.conv1d",
"model.language_model.layers.0.linear_attn.in_proj_a",
"model.language_model.layers.0.linear_attn.in_proj_b",
"model.language_model.layers.1.linear_attn.conv1d",
"model.language_model.layers.1.linear_attn.in_proj_a",
"model.language_model.layers.1.linear_attn.in_proj_b",
"model.language_model.layers.10.linear_attn.conv1d",
"model.language_model.layers.10.linear_attn.in_proj_a",
"model.language_model.layers.10.linear_attn.in_proj_b",
"model.language_model.layers.12.linear_attn.conv1d",
"model.language_model.layers.12.linear_attn.in_proj_a",
"model.language_model.layers.12.linear_attn.in_proj_b",
"model.language_model.layers.13.linear_attn.conv1d",
"model.language_model.layers.13.linear_attn.in_proj_a",
"model.language_model.layers.13.linear_attn.in_proj_b",
"model.language_model.layers.14.linear_attn.conv1d",
"model.language_model.layers.14.linear_attn.in_proj_a",
"model.language_model.layers.14.linear_attn.in_proj_b",
"model.language_model.layers.16.linear_attn.conv1d",
"model.language_model.layers.16.linear_attn.in_proj_a",
"model.language_model.layers.16.linear_attn.in_proj_b",
"model.language_model.layers.17.linear_attn.conv1d",
"model.language_model.layers.17.linear_attn.in_proj_a",
"model.language_model.layers.17.linear_attn.in_proj_b",
"model.language_model.layers.18.linear_attn.conv1d",
"model.language_model.layers.18.linear_attn.in_proj_a",
"model.language_model.layers.18.linear_attn.in_proj_b",
"model.language_model.layers.2.linear_attn.conv1d",
"model.language_model.layers.2.linear_attn.in_proj_a",
"model.language_model.layers.2.linear_attn.in_proj_b",
"model.language_model.layers.20.linear_attn.conv1d",
"model.language_model.layers.20.linear_attn.in_proj_a",
"model.language_model.layers.20.linear_attn.in_proj_b",
"model.language_model.layers.21.linear_attn.conv1d",
"model.language_model.layers.21.linear_attn.in_proj_a",
"model.language_model.layers.21.linear_attn.in_proj_b",
"model.language_model.layers.22.linear_attn.conv1d",
"model.language_model.layers.22.linear_attn.in_proj_a",
"model.language_model.layers.22.linear_attn.in_proj_b",
"model.language_model.layers.24.linear_attn.conv1d",
"model.language_model.layers.24.linear_attn.in_proj_a",
"model.language_model.layers.24.linear_attn.in_proj_b",
"model.language_model.layers.25.linear_attn.conv1d",
"model.language_model.layers.25.linear_attn.in_proj_a",
"model.language_model.layers.25.linear_attn.in_proj_b",
"model.language_model.layers.26.linear_attn.conv1d",
"model.language_model.layers.26.linear_attn.in_proj_a",
"model.language_model.layers.26.linear_attn.in_proj_b",
"model.language_model.layers.28.linear_attn.conv1d",
"model.language_model.layers.28.linear_attn.in_proj_a",
"model.language_model.layers.28.linear_attn.in_proj_b",
"model.language_model.layers.29.linear_attn.conv1d",
"model.language_model.layers.29.linear_attn.in_proj_a",
"model.language_model.layers.29.linear_attn.in_proj_b",
"model.language_model.layers.30.linear_attn.conv1d",
"model.language_model.layers.30.linear_attn.in_proj_a",
"model.language_model.layers.30.linear_attn.in_proj_b",
"model.language_model.layers.4.linear_attn.conv1d",
"model.language_model.layers.4.linear_attn.in_proj_a",
"model.language_model.layers.4.linear_attn.in_proj_b",
"model.language_model.layers.5.linear_attn.conv1d",
"model.language_model.layers.5.linear_attn.in_proj_a",
"model.language_model.layers.5.linear_attn.in_proj_b",
"model.language_model.layers.6.linear_attn.conv1d",
"model.language_model.layers.6.linear_attn.in_proj_a",
"model.language_model.layers.6.linear_attn.in_proj_b",
"model.language_model.layers.8.linear_attn.conv1d",
"model.language_model.layers.8.linear_attn.in_proj_a",
"model.language_model.layers.8.linear_attn.in_proj_b",
"model.language_model.layers.9.linear_attn.conv1d",
"model.language_model.layers.9.linear_attn.in_proj_a",
"model.language_model.layers.9.linear_attn.in_proj_b",
"model.visual*",
"mtp*",
"mtp.layers.0*"
],
"quant_algo": "MXFP8",
"producer": {
"name": "modelopt",
"version": "0.47.0.dev75+gfbcdc16c2.d20260818"
},
"quant_method": "modelopt"
}
}