Upload folder using huggingface_hub

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "alpindale/magnum-72b-v1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "group_size": 32,
+    "is_marlin_format": false,
+    "model_file_base_name": "gptq_model-4bit-32g",
+    "model_name_or_path": "magnum-gptq-32g",
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

gptq_model-4bit-32g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7becde4225e735de240aec992fb7426155ae852ae883cdd11eab8121400a7171
+size 45616409904

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "magnum-gptq-32g",
+  "model_file_base_name": "gptq_model-4bit-32g",
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}