TCYZ/ hayati:13m

15 2 months ago

0.4m 5m 13m
... /
model
33ef3a10b7e5 · 53MB
    Metadata
  • general.architecture
    llama
  • llama.attention.head_count
    2
  • llama.attention.head_count_kv
    2
  • llama.attention.layer_norm_rms_epsilon
    1e-05
  • llama.block_count
    1
  • 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]
  • output.weight
    F32
    [128, 50257]
  • output_norm.weight
    F32
    [128]