File size: 1,564 Bytes
6c48426 f142ca5 6c48426 f142ca5 6c48426 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
{
"a_ps": [
[
"dp",
"fsdp"
],
null,
"mp",
null
],
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_pdrop": 0.0,
"axis_dims": [
1,
-1,
1
],
"axis_names": [
"dp",
"fsdp",
"mp"
],
"b_ps": [
[
"dp",
"fsdp"
],
null,
"mp",
null
],
"backend": null,
"bits": null,
"bos_token_id": 0,
"embd_pdrop": 0.0,
"eos_token_id": 1,
"fcm_max_ratio": 0.0,
"fcm_min_ratio": 0.0,
"flash_attn_key_chunk_size": 128,
"flash_attn_query_chunk_size": 128,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1024,
"k_ps": [
[
"dp",
"fsdp"
],
null,
"mp",
null
],
"max_position_embeddings": 512,
"model_type": "llama",
"num_attention_heads": 8,
"num_hidden_layers": 16,
"num_key_value_heads": 4,
"number_rep_kv": 1,
"pretraining_tp": 1,
"q_ps": [
[
"dp",
"fsdp"
],
null,
"mp",
null
],
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"scan_layers": true,
"scan_mlp_chunk_size": 1024,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.0",
"use_cache": true,
"use_flash_attention": false,
"use_pjit_attention_force": false,
"use_sacn_mlp": false,
"use_shard_map": false,
"v_ps": [
[
"dp",
"fsdp"
],
null,
"mp",
null
],
"vocab_size": 32000
}
|