larryhudson/context-1-PreTrainedTokenizerFast
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: larryhudson/context-1-PreTrainedTokenizerFast
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 12:37:50 +08:00
commit 9e4449ed14
12 changed files with 622 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
config.json Normal file
View File

@@ -0,0 +1,69 @@
{
"architectures": [
"GptOssForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 200002,
"experts_per_token": 4,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2880,
"initial_context_length": 4096,
"initializer_range": 0.02,
"intermediate_size": 2880,
"layer_types": [
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 131072,
"model_type": "gpt_oss",
"num_attention_heads": 64,
"num_experts_per_tok": 4,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"num_local_experts": 32,
"output_router_logits": false,
"pad_token_id": 199999,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 32.0,
"original_max_position_embeddings": 4096,
"rope_theta": 150000,
"rope_type": "yarn",
"truncate": false
},
"router_aux_loss_coef": 0.9,
"sliding_window": 128,
"swiglu_limit": 7.0,
"tie_word_embeddings": false,
"transformers_version": "5.3.0",
"use_cache": true,
"vocab_size": 201088
}