初始化项目，由ModelHub XC社区提供模型

Model: BSC-LT/salamandra-2b-instruct_tools Source: Original Platform
2026-04-12 08:59:55 +08:00
commit ef149dd320
13 changed files with 11450 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/gpfs/projects/bsc88/text/models/instruction-tuning/models/base_models_with_special_tokens/restart_mix1_all_fineweb_2b_new_data_hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5440,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 256006
+}