5 3 days ago

vision
7159d31a6a6c · 11MB
    Metadata
  • general.architecture
    qwen35moe
  • general.file_type
    Q4_K_M
  • qwen35moe.attention.head_count
    32
  • qwen35moe.attention.head_count_kv
    2
  • qwen35moe.attention.key_length
    256
  • qwen35moe.attention.layer_norm_rms_epsilon
    1e-06
  • qwen35moe.attention.recurrent_layers
    [true, true, true, false, true, ...]
  • qwen35moe.attention.value_length
    256
  • qwen35moe.block_count
    49
  • qwen35moe.context_length
    262144
  • qwen35moe.embedding_length
    3072
  • qwen35moe.expert_count
    256
  • qwen35moe.expert_feed_forward_length
    1024
  • qwen35moe.expert_shared_feed_forward_length
    1024
  • qwen35moe.expert_used_count
    8
  • qwen35moe.full_attention_interval
    4
  • qwen35moe.nextn_predict_layers
    1
  • qwen35moe.rope.dimension_count
    64
  • qwen35moe.rope.dimension_sections
    [11, 11, 10, 0]
  • qwen35moe.rope.freq_base
    1e+07
  • qwen35moe.ssm.conv_kernel
    4
  • qwen35moe.ssm.group_count
    16
  • qwen35moe.ssm.inner_size
    8192
  • qwen35moe.ssm.state_size
    128
  • qwen35moe.ssm.time_step_rank
    64
  • tokenizer.ggml.add_bos_token
    false
  • tokenizer.ggml.add_eos_token
    false
  • tokenizer.ggml.eos_token_id
    248046
  • tokenizer.ggml.merges
    [Ġ Ġ, ĠĠ ĠĠ, i n, Ġ t, ĠĠĠĠ ĠĠĠĠ, ...]
  • tokenizer.ggml.model
    gpt2
  • tokenizer.ggml.normalizer.nfc
    true
  • tokenizer.ggml.padding_token_id
    248044
  • tokenizer.ggml.pre
    qwen35
  • tokenizer.ggml.token_type
    [1, 1, 1, 1, 1, ...]
  • tokenizer.ggml.tokens
    [!, ", #, $, %, ...]
  • split.count
    3
  • split.no
    0
  • split.tensors.count
    899
  • Tensor