Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "quantization_config": {
+    "act_bits": 16,
+    "act_data_type": "int",
+    "act_dynamic": true,
+    "act_group_size": 128,
+    "act_sym": false,
+    "amp": true,
+    "autoround_version": "0.4.7",
+    "batch_size": 8,
+    "bits": 4,
+    "damp_percent": 0.01,
+    "data_type": "int",
+    "desc_act": false,
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "gradient_accumulate_steps": 1,
+    "group_size": 128,
+    "iters": 1000,
+    "low_gpu_mem_usage": true,
+    "lr": 0.001,
+    "minmax_lr": 0.001,
+    "nsamples": 512,
+    "quant_method": "gptq",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "super_bits": null,
+    "super_group_size": null,
+    "sym": false,
+    "to_quant_block_names": null,
+    "true_sequential": false
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.1",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.9",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}