scb10x/llama3.2-typhoon2-1b
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: scb10x/llama3.2-typhoon2-1b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 13:25:36 +08:00
commit f1291c544a
9 changed files with 2209 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 @@
{"_name_or_path": "./", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.45.1", "use_cache": false, "vocab_size": 128256}