Files
sft__ot30k_SmolLM2-1.7B-Ins…/config.json
ModelHub XC 56a5744455 初始化项目,由ModelHub XC社区提供模型
Model: open-sci/sft__ot30k_SmolLM2-1.7B-Instruct-16k
Source: Original Platform
2026-04-28 06:43:07 +08:00

37 lines
812 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers.js_config": {
"kv_cache_dtype": {
"fp16": "float16",
"q4f16": "float16"
}
},
"transformers_version": "4.55.0",
"use_cache": false,
"vocab_size": 49152
}