TCYZ/ cokertme2:14m

45 1 month ago

Çökertme 2, Türkçe doğal dil işleme görevleri için optimize edilmiş, ultra-nano ölçekli bir dil modeli ailesidir.

0.8m 1.6m 5m 6m 14m 100m
... /
model
23bf1c78eafb · 57MB
    Metadata
  • general.architecture
    llama
  • llama.attention.head_count
    8
  • llama.attention.head_count_kv
    8
  • llama.attention.layer_norm_rms_epsilon
    1e-05
  • llama.block_count
    6
  • llama.context_length
    128
  • llama.embedding_length
    128
  • llama.feed_forward_length
    341
  • tokenizer.ggml.model
    llama
  • tokenizer.ggml.scores
    [0, 0, 0, 0, 0, ...]
  • tokenizer.ggml.token_type
    [1, 1, 1, 1, 1, ...]
  • tokenizer.ggml.tokens
    [!, ", #, $, %, ...]
    • Tensor
  • token_embd.weight
    F32
    [128, 50257]
    • blk.0
  • blk.0.attn_k.weight
    F32
    [128, 128]
  • blk.0.attn_norm.weight
    F32
    [128]
  • blk.0.attn_output.weight
    F32
    [128, 128]
  • blk.0.attn_q.weight
    F32
    [128, 128]
  • blk.0.attn_v.weight
    F32
    [128, 128]
  • blk.0.ffn_down.weight
    F32
    [341, 128]
  • blk.0.ffn_gate.weight
    F32
    [128, 341]
  • blk.0.ffn_norm.weight
    F32
    [128]
  • blk.0.ffn_up.weight
    F32
    [128, 341]
    • blk.1
  • blk.1.attn_k.weight
    F32
    [128, 128]
  • blk.1.attn_norm.weight
    F32
    [128]
  • blk.1.attn_output.weight
    F32
    [128, 128]
  • blk.1.attn_q.weight
    F32
    [128, 128]
  • blk.1.attn_v.weight
    F32
    [128, 128]
  • blk.1.ffn_down.weight
    F32
    [341, 128]
  • blk.1.ffn_gate.weight
    F32
    [128, 341]
  • blk.1.ffn_norm.weight
    F32
    [128]
  • blk.1.ffn_up.weight
    F32
    [128, 341]
    • blk.2
  • blk.2.attn_k.weight
    F32
    [128, 128]
  • blk.2.attn_norm.weight
    F32
    [128]
  • blk.2.attn_output.weight
    F32
    [128, 128]
  • blk.2.attn_q.weight
    F32
    [128, 128]
  • blk.2.attn_v.weight
    F32
    [128, 128]
  • blk.2.ffn_down.weight
    F32
    [341, 128]
  • blk.2.ffn_gate.weight
    F32
    [128, 341]
  • blk.2.ffn_norm.weight
    F32
    [128]
  • blk.2.ffn_up.weight
    F32
    [128, 341]
    • blk.3
  • blk.3.attn_k.weight
    F32
    [128, 128]
  • blk.3.attn_norm.weight
    F32
    [128]
  • blk.3.attn_output.weight
    F32
    [128, 128]
  • blk.3.attn_q.weight
    F32
    [128, 128]
  • blk.3.attn_v.weight
    F32
    [128, 128]
  • blk.3.ffn_down.weight
    F32
    [341, 128]
  • blk.3.ffn_gate.weight
    F32
    [128, 341]
  • blk.3.ffn_norm.weight
    F32
    [128]
  • blk.3.ffn_up.weight
    F32
    [128, 341]
    • blk.4
  • blk.4.attn_k.weight
    F32
    [128, 128]
  • blk.4.attn_norm.weight
    F32
    [128]
  • blk.4.attn_output.weight
    F32
    [128, 128]
  • blk.4.attn_q.weight
    F32
    [128, 128]
  • blk.4.attn_v.weight
    F32
    [128, 128]
  • blk.4.ffn_down.weight
    F32
    [341, 128]
  • blk.4.ffn_gate.weight
    F32
    [128, 341]
  • blk.4.ffn_norm.weight
    F32
    [128]
  • blk.4.ffn_up.weight
    F32
    [128, 341]
    • blk.5
  • blk.5.attn_k.weight
    F32
    [128, 128]
  • blk.5.attn_norm.weight
    F32
    [128]
  • blk.5.attn_output.weight
    F32
    [128, 128]
  • blk.5.attn_q.weight
    F32
    [128, 128]
  • blk.5.attn_v.weight
    F32
    [128, 128]
  • blk.5.ffn_down.weight
    F32
    [341, 128]
  • blk.5.ffn_gate.weight
    F32
    [128, 341]
  • blk.5.ffn_norm.weight
    F32
    [128]
  • blk.5.ffn_up.weight
    F32
    [128, 341]
  • output.weight
    F32
    [128, 50257]
  • output_norm.weight
    F32
    [128]