Upload merged model and tokenizer in safetensors format

config.json

@@ -1,34 +1,30 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "arnir0/Tiny-LLM",
-  "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "k_proj",
-    "dense",
-    "v_proj"
+  "_name_or_path": "arnir0/Tiny-LLM",
+  "architectures": [
+    "LlamaForCausalLM"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 192,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206fdbdcc482ac21e6ab824900b6e1ab5136db75fe77db59cf47833c7035a8a5
-size 123680
+oid sha256:8bf61a2f92311133fbbae607a6e5d798c543d6a71be2049a1f74f79543a86dbc
+size 51957256