初始化项目,由ModelHub XC社区提供模型

Model: ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-19 08:24:02 +08:00
commit 297a1153ec
18 changed files with 147863 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 10928,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.40.2",
"use_cache": true,
"vocab_size": 49152
}