auto_gptq format

Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>

config.json

@@ -24,8 +24,9 @@
     "autoround_version": "0.4.2",
     "batch_size": 8,
     "bits": 4,
+    "damp_percent": 0.01,
     "data_type": "int",
-    "dataset": "NeelNanda/pile-10k",
+    "desc_act": false,
     "enable_minmax_tuning": true,
     "enable_norm_bias_tuning": false,
     "enable_quanted_input": true,
@@ -35,17 +36,13 @@
     "low_gpu_mem_usage": false,
     "lr": 0.001,
     "minmax_lr": 0.001,
-    "modules_to_not_convert": [
-      "lm_head"
-    ],
     "nsamples": 512,
-    "quant_method": "awq",
+    "quant_method": "gptq",
     "scale_dtype": "torch.float16",
     "seqlen": 2048,
     "sym": true,
     "to_quant_block_names": null,
-    "version": "gemm",
-    "zero_point": false
+    "true_sequential": false
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc45bcfbe23bc67e9b4c1543f10680449e67371e2fc85fba6476d8043f85a5da
-size 4260648608
+oid sha256:9fd9757a889168c288a4bba9b7d65deb2bb3075b1c85e7492c97170facef500d
+size 4265314752

model.safetensors.index.json

@@ -1,651 +1,847 @@
 {
   "metadata": {
-    "total_size": 5065881600
+    "total_size": 5070526464
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",

quantization_config.json → quantize_config.json

@@ -17,12 +17,9 @@
   "low_gpu_mem_usage": false,
   "to_quant_block_names": null,
   "enable_norm_bias_tuning": false,
-  "dataset": "NeelNanda/pile-10k",
   "autoround_version": "0.4.2",
-  "quant_method": "awq",
-  "zero_point": false,
-  "version": "gemm",
-  "modules_to_not_convert": [
-    "lm_head"
-  ]
+  "quant_method": "gptq",
+  "desc_act": false,
+  "true_sequential": false,
+  "damp_percent": 0.01
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {