unclemusclez / unsloth-yi-coder-devinator

1.5b

4 weeks ago

18 Tags
... /
model
fe88007f9dbb · 872MB
    Metadata
  • general.architecture
    llama
  • general.base_model.0.name
    Yi Coder 1.5B Chat
  • general.base_model.0.organization
    01 Ai
  • general.base_model.0.repo_url
    https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat
  • general.base_model.count
    1
  • general.basename
    Yi-Coder
  • general.datasets
    [skratos115/opendevin_DataDevinator]
  • general.file_type
    25
  • general.finetune
    Chat
  • general.license
    other
  • general.name
    Yi Coder 1.5B Chat
  • general.organization
    01 Ai
  • general.quantization_version
    2
  • general.size_label
    1.5B
  • general.tags
    [autotrain, text-generation-inference, text-generation, peft]
  • general.type
    model
  • llama.attention.head_count
    16
  • llama.attention.head_count_kv
    16
  • llama.attention.key_length
    128
  • llama.attention.layer_norm_rms_epsilon
    1e-05
  • llama.attention.value_length
    128
  • llama.block_count
    24
  • llama.context_length
    131072
  • llama.embedding_length
    2048
  • llama.feed_forward_length
    5504
  • llama.rope.dimension_count
    128
  • llama.rope.freq_base
    1e+07
  • llama.vocab_size
    64000
  • tokenizer.ggml.add_bos_token
    false
  • tokenizer.ggml.add_eos_token
    false
  • tokenizer.ggml.add_space_prefix
    false
  • tokenizer.ggml.bos_token_id
    1
  • tokenizer.ggml.eos_token_id
    7
  • tokenizer.ggml.model
    llama
  • tokenizer.ggml.padding_token_id
    0
  • tokenizer.ggml.pre
    default
  • tokenizer.ggml.scores
    [-1000, -1000, -1000, -1000, -1000, ...]
  • tokenizer.ggml.token_type
    [3, 3, 3, 3, 3, ...]
  • tokenizer.ggml.tokens
    [<unk>, <|startoftext|>, <|endoftext|>, <|Human|>, <|Assistant|>, ...]
  • tokenizer.ggml.unknown_token_id
    0
    • Tensor
  • Name
    Type
    Shape
  • token_embd.weight
    (!unknown_type 20!)
    [2048, 64000]
    • blk.0
  • blk.0.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.0.attn_norm.weight
    F32
    [2048]
  • blk.0.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.0.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.0.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.0.ffn_down.weight
    Q5_1
    [5504, 2048]
  • blk.0.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.0.ffn_norm.weight
    F32
    [2048]
  • blk.0.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.1
  • blk.1.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.1.attn_norm.weight
    F32
    [2048]
  • blk.1.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.1.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.1.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.1.ffn_down.weight
    Q5_1
    [5504, 2048]
  • blk.1.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.1.ffn_norm.weight
    F32
    [2048]
  • blk.1.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.2
  • blk.2.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.2.attn_norm.weight
    F32
    [2048]
  • blk.2.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.2.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.2.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.2.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.2.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.2.ffn_norm.weight
    F32
    [2048]
  • blk.2.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.3
  • blk.3.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.3.attn_norm.weight
    F32
    [2048]
  • blk.3.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.3.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.3.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.3.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.3.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.3.ffn_norm.weight
    F32
    [2048]
  • blk.3.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.4
  • blk.4.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.4.attn_norm.weight
    F32
    [2048]
  • blk.4.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.4.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.4.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.4.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.4.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.4.ffn_norm.weight
    F32
    [2048]
  • blk.4.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.5
  • blk.5.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.5.attn_norm.weight
    F32
    [2048]
  • blk.5.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.5.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.5.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.5.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.5.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.5.ffn_norm.weight
    F32
    [2048]
  • blk.5.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.6
  • blk.6.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.6.attn_norm.weight
    F32
    [2048]
  • blk.6.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.6.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.6.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.6.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.6.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.6.ffn_norm.weight
    F32
    [2048]
  • blk.6.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.7
  • blk.7.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.7.attn_norm.weight
    F32
    [2048]
  • blk.7.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.7.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.7.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.7.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.7.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.7.ffn_norm.weight
    F32
    [2048]
  • blk.7.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.8
  • blk.8.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.8.attn_norm.weight
    F32
    [2048]
  • blk.8.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.8.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.8.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.8.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.8.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.8.ffn_norm.weight
    F32
    [2048]
  • blk.8.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.9
  • blk.9.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.9.attn_norm.weight
    F32
    [2048]
  • blk.9.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.9.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.9.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.9.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.9.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.9.ffn_norm.weight
    F32
    [2048]
  • blk.9.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.10
  • blk.10.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.10.attn_norm.weight
    F32
    [2048]
  • blk.10.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.10.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.10.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.10.ffn_down.weight
    Q5_1
    [5504, 2048]
  • blk.10.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.10.ffn_norm.weight
    F32
    [2048]
  • blk.10.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.11
  • blk.11.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.11.attn_norm.weight
    F32
    [2048]
  • blk.11.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.11.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.11.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.11.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.11.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.11.ffn_norm.weight
    F32
    [2048]
  • blk.11.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.12
  • blk.12.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.12.attn_norm.weight
    F32
    [2048]
  • blk.12.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.12.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.12.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.12.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.12.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.12.ffn_norm.weight
    F32
    [2048]
  • blk.12.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.13
  • blk.13.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.13.attn_norm.weight
    F32
    [2048]
  • blk.13.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.13.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.13.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.13.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.13.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.13.ffn_norm.weight
    F32
    [2048]
  • blk.13.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.14
  • blk.14.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.14.attn_norm.weight
    F32
    [2048]
  • blk.14.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.14.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.14.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.14.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.14.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.14.ffn_norm.weight
    F32
    [2048]
  • blk.14.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.15
  • blk.15.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.15.attn_norm.weight
    F32
    [2048]
  • blk.15.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.15.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.15.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.15.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.15.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.15.ffn_norm.weight
    F32
    [2048]
  • blk.15.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.16
  • blk.16.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.16.attn_norm.weight
    F32
    [2048]
  • blk.16.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.16.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.16.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.16.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.16.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.16.ffn_norm.weight
    F32
    [2048]
  • blk.16.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.17
  • blk.17.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.17.attn_norm.weight
    F32
    [2048]
  • blk.17.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.17.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.17.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.17.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.17.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.17.ffn_norm.weight
    F32
    [2048]
  • blk.17.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.18
  • blk.18.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.18.attn_norm.weight
    F32
    [2048]
  • blk.18.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.18.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.18.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.18.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.18.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.18.ffn_norm.weight
    F32
    [2048]
  • blk.18.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.19
  • blk.19.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.19.attn_norm.weight
    F32
    [2048]
  • blk.19.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.19.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.19.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.19.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.19.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.19.ffn_norm.weight
    F32
    [2048]
  • blk.19.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.20
  • blk.20.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.20.attn_norm.weight
    F32
    [2048]
  • blk.20.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.20.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.20.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.20.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.20.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.20.ffn_norm.weight
    F32
    [2048]
  • blk.20.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.21
  • blk.21.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.21.attn_norm.weight
    F32
    [2048]
  • blk.21.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.21.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.21.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.21.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.21.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.21.ffn_norm.weight
    F32
    [2048]
  • blk.21.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.22
  • blk.22.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.22.attn_norm.weight
    F32
    [2048]
  • blk.22.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.22.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.22.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.22.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.22.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.22.ffn_norm.weight
    F32
    [2048]
  • blk.22.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
    • blk.23
  • blk.23.attn_k.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.23.attn_norm.weight
    F32
    [2048]
  • blk.23.attn_output.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.23.attn_q.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.23.attn_v.weight
    (!unknown_type 20!)
    [2048, 2048]
  • blk.23.ffn_down.weight
    (!unknown_type 20!)
    [5504, 2048]
  • blk.23.ffn_gate.weight
    (!unknown_type 20!)
    [2048, 5504]
  • blk.23.ffn_norm.weight
    F32
    [2048]
  • blk.23.ffn_up.weight
    (!unknown_type 20!)
    [2048, 5504]
  • output.weight
    Q6_K
    [2048, 64000]
  • output_norm.weight
    F32
    [2048]