add config files

config.json

@@ -0,0 +1,30 @@
+{
+ "_name_or_path": "/gpfs/projects/bsc88/text/models/instruction-tuning/models/base_models_with_special_tokens/bsc_2b_4thepoch_hf",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "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,
+ "num_layers": 24,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.40.2",
+ "use_cache": true,
+ "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": [
+ 2,
+ 5
+ ],
+ "do_sample": true,
+ "temperature": 0.6,
+ "repetition_penalty": 1.2,
+ "transformers_version": "4.40.2"
+}