b681f25400
Model: ali-elganzory/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-16k-SFT-Tulu3-decontaminated Source: Original Platform
38 lines
946 B
JSON
38 lines
946 B
JSON
{
|
|
"architectures": [
|
|
"OpensciForCausalLM"
|
|
],
|
|
"attention_bias": true,
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_opensci.OpensciConfig",
|
|
"AutoModel": "modeling_opensci.OpensciModel",
|
|
"AutoModelForCausalLM": "modeling_opensci.OpensciForCausalLM"
|
|
},
|
|
"bos_token_id": 0,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 50277,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8192,
|
|
"layer_norm_eps": 1e-05,
|
|
"max_position_embeddings": 16384,
|
|
"mlp_bias": true,
|
|
"model_type": "opensci",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 32,
|
|
"pad_token_id": 50277,
|
|
"pretraining_tp": 1,
|
|
"qk_layernorm": true,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": true,
|
|
"vocab_size": 50304
|
|
}
|