Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 131072,
+  "rope_scaling": {
+    "type": "yarn",
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768
+  },
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": 1.3719201493514375,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093c045fa9ff737a37016f56452875a90314d8dd598314e66153cd0d174437df
+size 4961926344

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604ab895722ecc702dbc3a38384a0ecc6d84f947fe5dd68f102e1dc865d55206
+size 4997213928

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965e91c686ad8e55d0691f223436c668052c081272b211206fe277446be91938
+size 4994066776

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc1d9ac1cad61d4988f654d21514529bb39b9348572b84bf2dbc372f98b81db
+size 4893355368

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03bd1373037991bf3c3fc91d5b73002613909e1a65ccd0778d1f1c2e3a6ad04
+size 4751767312

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29365d720c66e0ebc02ad25dbbe3777c733e601376ac2515bf732044cbf61015
+size 4997213992

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1aecfa08bff703b55e0f79db8dbb47e9e6292ff23a5c40ad78ee6afc49dc31
+size 4842360552

model.safetensors.index.json

@@ -0,0 +1,986 @@
+{
+  "metadata": {
+    "total_size": 34437790720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.post_mlp_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.post_self_attn_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.post_mlp_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.post_self_attn_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.35.mlp.gate_up_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.gate_up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.gate_up_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.post_mlp_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.post_self_attn_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_self_attn_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.52.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.53.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.mlp.gate_up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.mlp.gate_up_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.post_mlp_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.post_self_attn_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.54.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.55.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.55.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.55.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.55.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.55.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.56.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.k_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.q_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.56.self_attn.v_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.k_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.q_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.57.self_attn.v_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.k_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.q_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.58.self_attn.v_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.k_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.q_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.59.self_attn.v_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.mlp.down_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.60.mlp.gate_up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.mlp.gate_up_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.post_mlp_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.post_self_attn_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.k_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.o_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.q_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.60.self_attn.v_proj.weight_scale": "model-00007-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_mlp_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_self_attn_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

recipe.yaml

@@ -0,0 +1,6 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      ignore: [lm_head]
+      targets: [Linear]
+      scheme: FP8_DYNAMIC

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n你是一个名为 ChatGLM 的人工智能助手。你是基于智谱 AI 公司训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。\n\n# 可用工具\n{%- for tool in tools %}\n    {%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4, ensure_ascii=False) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。\n{%- endfor %}\n{%- endif -%}\n\n{%- for msg in messages %}\n    {%- if msg.role == 'system' %}\n<|system|>\n{{ msg.content }}\n    {%- endif %}\n{%- endfor %}\n\n{%- for message in messages if message.role != 'system' %}\n    {%- set role = message['role'] %}\n    {%- set content = message['content'] %}\n    {%- set visible = content.split('</think>')[-1].strip() %}\n    {%- set meta = message.get(\"metadata\", \"\") %}\n\n    {%- if role == 'user' %}\n<|user|>\n{{ visible }}\n    {%- elif role == 'assistant' and not meta %}\n<|assistant|>\n{{ visible }}\n    {%- elif role == 'assistant' and meta %}\n<|assistant|>{{ meta }}\n{{ visible }}\n    {%- elif role == 'observation' %}\n<|observation|>\n{{ visible }}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}<|assistant|>\\n<think>{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}