coder11v/ ashermodel:latest

4 days ago

... /
model
badb3e89215e ยท 56kB
    Metadata
  • general.architecture
    llama
  • llama.attention.head_count
    1
  • llama.attention.head_count_kv
    1
  • llama.attention.layer_norm_rms_epsilon
    1e-05
  • llama.block_count
    1
  • llama.context_length
    2048
  • llama.embedding_length
    16
  • llama.feed_forward_length
    48
  • tokenizer.ggml.bos_token_id
    1
  • tokenizer.ggml.eos_token_id
    2
  • tokenizer.ggml.model
    llama
  • tokenizer.ggml.scores
    [-100, -100, -100, 0, 0, ...]
  • tokenizer.ggml.token_type
    [1, 1, 1, 1, 1, ...]
  • tokenizer.ggml.tokens
    [<unk>, <s>, </s>, H, e, ...]
  • tokenizer.ggml.unk_token_id
    0
    • Tensor
  • token_embd.weight
    F32
    [16, 275]
    • blk.0
  • blk.0.attn_k.weight
    F32
    [16, 16]
  • blk.0.attn_norm.weight
    F32
    [16]
  • blk.0.attn_output.weight
    F32
    [16, 16]
  • blk.0.attn_q.weight
    F32
    [16, 16]
  • blk.0.attn_v.weight
    F32
    [16, 16]
  • blk.0.ffn_down.weight
    F32
    [48, 16]
  • blk.0.ffn_gate.weight
    F32
    [16, 48]
  • blk.0.ffn_norm.weight
    F32
    [16]
  • blk.0.ffn_up.weight
    F32
    [16, 48]
  • output.weight
    F32
    [16, 275]
  • output_norm.weight
    F32
    [16]