Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "QwenForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_qwen.QwenConfig",
+    "AutoModelForCausalLM": "modeling_qwen.QwenLMHeadModel"
+  },
+  "bf16": false,
+  "embd_pdrop": 0.0,
+  "fp16": false,
+  "fp32": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 32768,
+  "model_type": "qwen",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "use_flash_attn": "auto",
+  "vocab_size": 151936,
+  "hidden_size": 3584,
+  "character": "Passionate AI development instructor with deep insights",
+  "training_samples": 38,
+  "quantization": "Q8_0",
+  "model_size_gb": 4.3,
+  "quality_level": "Extremely High",
+  "base_model": "bartowski/Menlo_Jan-nano-GGUF",
+  "quality_score": 9.5,
+  "improvements_over_iq4xs": [
+    "15%+ response quality improvement",
+    "Better Japanese nuance understanding",
+    "More consistent character personality",
+    "Enhanced technical knowledge retention",
+    "Improved logical reasoning capabilities"
+  ]
+}