TokenRhythm/ neohorse-1:4b-mlx-8bit

377 3 weeks ago

tools thinking
... /
json
ab301022c909 · 2.4kB
{
"architectures": [
"Qwen3_5ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": [
248044,
248046
],
"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,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5",
"modification_notice": "Modified by TokenRhythm: language-model weights fine-tuned from Qwen/Qwen3.5-4B; repackaged for text-only inference by changing config and tensor key prefixes. Tensor values are unchanged by repackaging. Original model: Copyright 2026 Alibaba Cloud.",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"quantization": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_theta": 10000000,
"partial_rotary_factor": 0.25,
"type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.16.1",
"use_cache": true,
"vocab_size": 248320
}