Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google/gemma-2-9b-it",
+  "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": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.025,
+    "desc_act": true,
+    "exponent_hinv": 4.0,
+    "group_size": 128,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "shrink": 0.0625,
+    "static_groups": false,
+    "sym": false,
+    "true_sequential": true
+  },
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 256000
+}

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdaaca6a67fef734e163ff7217eeacd0c93246a8f00b2857d50051218070f42
+size 8001855472

quantize_config.json

@@ -0,0 +1,15 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.025,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": false,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "exponent_hinv": 4.0,
+  "shrink": 0.0625,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
+}