Upload config.json with huggingface_hub

config.json

@@ -2,49 +2,28 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "dtype": "float16",
-  "eos_token_id": 128001,
-  "head_dim": 128,
+  "auto_map": {
+    "AutoConfig": "configuration_llama.LlamaConfig",
+    "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 128004,
+  "num_key_value_heads": 32,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "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": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.1",
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.9.5",
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 128256
-}
+}