Upload config.json

config.json

@@ -1,29 +1,41 @@
 {
-  "_name_or_path": "harry85/TinyLLAMA-finetuned-own-data",
+  "_name_or_path": "unsloth/tinyllama",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
   "use_cache": true,
-  "vocab_size": 128264
-}
+  "vocab_size": 32000
+}