(Trained with Unsloth)

config.json

@@ -1,48 +1,3 @@
 {
-  "_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
-  "architectures": [
-    "Gemma2ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": 50.0,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": 1,
-  "final_logit_softcapping": 30.0,
-  "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3584,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 42,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "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"
-  },
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "sliding_window_size": 4096,
-  "torch_dtype": "float16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9.post4",
-  "use_cache": true,
-  "vocab_size": 256000
-}
+    "model_type": "gemma2"
+}