typhoon-ai/typhoon2.1-gemma3-4b
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: typhoon-ai/typhoon2.1-gemma3-4b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-05 09:42:17 +08:00
commit 8aeb61000c
12 changed files with 52184 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
config.json Normal file
View File

@@ -0,0 +1 @@
{"architectures": ["Gemma3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": null, "bos_token_id": 2, "cache_implementation": "hybrid", "eos_token_id": 1, "final_logit_softcapping": null, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 10240, "max_position_embeddings": 131072, "model_type": "gemma3_text", "num_attention_heads": 8, "num_hidden_layers": 34, "num_key_value_heads": 4, "pad_token_id": 0, "query_pre_attn_scalar": 256, "rms_norm_eps": 1e-06, "rope_local_base_freq": 10000.0, "rope_scaling": {"factor": 8.0, "rope_type": "linear"}, "rope_theta": 1000000.0, "sliding_window": 1024, "sliding_window_pattern": 6, "torch_dtype": "bfloat16", "transformers_version": "4.50.0.dev0", "use_cache": false, "vocab_size": 262145, "_name_or_path": "./"}