Updated with 4.5 bpw quantized model files

config.json

@@ -1,28 +1,39 @@
 {
-  "_name_or_path": "MaziyarPanahi/calme-3-selfmerge-qwen2-78b",
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "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": 86,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.1",
-  "use_cache": false,
-  "use_sliding_window": false,
-  "vocab_size": 151646
-}
+    "_name_or_path": "MaziyarPanahi/calme-3-selfmerge-qwen2-78b",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "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": 86,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.1",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151646,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.7",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31dc06995917e02ca1a3a04bb5c6041b4a224ad593a519d7b1e9b9e1edc4261c
+size 8575846954

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f72d5381762172b573121c9898094fc1b3ae8de3ec6f35a9873abd3fdedf552
+size 8554424834

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bdfde657cd67daf826bcf85e1c31eb23e4b63f362c5dcc494cf5c9034a8c355
+size 8589246528

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38720100c8dfe7a447256d15b0a961e3a28231cb7be9dcd351d37a299845362
+size 8576427954

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32707603d7a09b6803fb6eddd4bded9313afa85e013d9db1dc52ebbc094b3cd
+size 6899992970

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266