first commit

Signed-off-by: wenhuach <wenhuach87@gmail.com>

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "/models/falcon-three-10b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "amp": true,
+    "autoround_version": "0.4.2",
+    "batch_size": 8,
+    "bits": 4,
+    "data_type": "int",
+    "dataset": "NeelNanda/pile-10k",
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "gradient_accumulate_steps": 1,
+    "group_size": 128,
+    "iters": 1000,
+    "low_gpu_mem_usage": false,
+    "lr": 0.001,
+    "minmax_lr": 0.001,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "nsamples": 512,
+    "quant_method": "awq",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "sym": true,
+    "to_quant_block_names": null,
+    "version": "gemm",
+    "zero_point": false
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.47.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999c5fb4dad66da10c5a8621d9eff86cf674e93f22315a581592e4095a8f66c1
+size 4999953032

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abf746502106c32f1ed2c6947e0ac245f6e00cec9acdefffeda80980319994c
+size 1546860320

model.safetensors.index.json

@@ -0,0 +1,930 @@
+{
+  "metadata": {
+    "total_size": 6546708480
+  },
+  "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.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.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.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.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.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.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.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.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.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

quantization_config.json

@@ -0,0 +1,28 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 2048,
+  "batch_size": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 0.001,
+  "minmax_lr": 0.001,
+  "gradient_accumulate_steps": 1,
+  "iters": 1000,
+  "amp": true,
+  "nsamples": 512,
+  "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"
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}