Upload folder using huggingface_hub

mlc-chat-config.json

@@ -11,19 +11,21 @@
     "num_key_value_heads": 4,
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
-    "vocab_size": 152064,
+    "vocab_size": 136488,
     "tie_word_embeddings": false,
-    "context_window_size": 512,
-    "prefill_chunk_size": 512,
+    "context_window_size": 256,
+    "prefill_chunk_size": 128,
     "tensor_parallel_shards": 1,
     "head_dim": 128,
     "dtype": "float32",
-    "max_batch_size": 128
+    "max_batch_size": 1
   },
-  "vocab_size": 152064,
-  "context_window_size": 512,
+  "context_length": 512,
+  "max_tokens": 128,
+  "vocab_size": 136488,
+  "context_window_size": 256,
   "sliding_window_size": -1,
-  "prefill_chunk_size": 512,
+  "prefill_chunk_size": 128,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,
@@ -45,13 +47,13 @@
   },
   "conv_template": {
     "name": "qwen2",
-    "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
+    "system_template": "system\n{system_message}\n",
     "system_message": "You are a helpful assistant.",
     "system_prefix_token_ids": null,
     "add_role_after_system_message": true,
     "roles": {
-      "user": "<|im_start|>user",
-      "assistant": "<|im_start|>assistant"
+      "user": "user",
+      "assistant": "assistant"
     },
     "role_templates": {
       "user": "{user_message}",
@@ -60,25 +62,21 @@
     },
     "messages": [],
     "seps": [
-      "<|im_end|>\n"
+      "\n"
     ],
     "role_content_sep": "\n",
     "role_empty_sep": "\n",
     "stop_str": [
-      "<|endoftext|>",
-      "<|im_end|>"
+      "\n\n"
     ],
     "stop_token_ids": [
-      151643,
-      151645
+      136487,
+      136485
     ],
     "function_string": "",
     "use_function_calling": false
   },
-  "pad_token_id": 151643,
-  "bos_token_id": 151643,
-  "eos_token_id": [
-    151645,
-    151643
-  ]
+  "pad_token_id": 136485,
+  "bos_token_id": 136485,
+  "eos_token_id": 136487
 }

ndarray-cache.json

@@ -1,47 +1,47 @@
 {
     "metadata": {
         "ParamSize": 31,
-        "ParamBytes": 4044459008.0,
+        "ParamBytes": 3821161472.0,
         "BitsPerParam": 16.0
     },
     "records": [
         {
             "dataPath": "params_shard_0.bin",
             "format": "raw-shard",
-            "nbytes": 1089994752,
+            "nbytes": 978345984,
             "records": [
                 {
-                    "name": "model.embed_tokens.weight",
+                    "name": "lm_head.weight",
                     "shape": [
-                        152064,
+                        136488,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 1089994752,
+                    "nbytes": 978345984,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "04271b91cafad82f630343dcc1156d75"
+            "md5sum": "f24bc2a390a565ec24307333d9aa9b5b"
         },
         {
             "dataPath": "params_shard_1.bin",
             "format": "raw-shard",
-            "nbytes": 25690112,
+            "nbytes": 135790592,
             "records": [
                 {
-                    "name": "model.layers.0.self_attn.o_proj.weight",
+                    "name": "model.layers.3.mlp.down_proj.weight",
                     "shape": [
                         3584,
-                        3584
+                        18944
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 25690112,
+                    "nbytes": 135790592,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "23278f4c2c2bd26e27c57bf98ad4ef8c"
+            "md5sum": "8463225b5d39d8aa6befc7e394ff9a80"
         },
         {
             "dataPath": "params_shard_2.bin",
@@ -49,7 +49,7 @@
             "nbytes": 271581184,
             "records": [
                 {
-                    "name": "model.layers.0.mlp.gate_up_proj.weight",
+                    "name": "model.layers.3.mlp.gate_up_proj.weight",
                     "shape": [
                         37888,
                         3584
@@ -60,83 +60,83 @@
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "eab8149d005afce177602e3a0502e2d5"
+            "md5sum": "ce9430ea30508f4c11646d9f6987c7d5"
         },
         {
             "dataPath": "params_shard_3.bin",
             "format": "raw-shard",
-            "nbytes": 135790592,
+            "nbytes": 978345984,
             "records": [
                 {
-                    "name": "model.layers.0.mlp.down_proj.weight",
+                    "name": "model.embed_tokens.weight",
                     "shape": [
-                        3584,
-                        18944
+                        136488,
+                        3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 135790592,
+                    "nbytes": 978345984,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "d8c5636ba8c54a1bf9a9be52028edd24"
+            "md5sum": "2034469190648e591720406f8f5d6931"
         },
         {
             "dataPath": "params_shard_4.bin",
             "format": "raw-shard",
-            "nbytes": 33030144,
+            "nbytes": 135790592,
             "records": [
                 {
-                    "name": "model.layers.1.self_attn.c_attn.weight",
+                    "name": "model.layers.0.mlp.down_proj.weight",
                     "shape": [
-                        4608,
-                        3584
+                        3584,
+                        18944
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 33030144,
+                    "nbytes": 135790592,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "c03154c2e7e28390bd1554a72a582034"
+            "md5sum": "d8c5636ba8c54a1bf9a9be52028edd24"
         },
         {
             "dataPath": "params_shard_5.bin",
             "format": "raw-shard",
-            "nbytes": 25690112,
+            "nbytes": 271581184,
             "records": [
                 {
-                    "name": "model.layers.1.self_attn.o_proj.weight",
+                    "name": "model.layers.0.mlp.gate_up_proj.weight",
                     "shape": [
-                        3584,
+                        37888,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 25690112,
+                    "nbytes": 271581184,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "d46398b81504bd2d82830108afdd8407"
+            "md5sum": "eab8149d005afce177602e3a0502e2d5"
         },
         {
             "dataPath": "params_shard_6.bin",
             "format": "raw-shard",
-            "nbytes": 271581184,
+            "nbytes": 25690112,
             "records": [
                 {
-                    "name": "model.layers.1.mlp.gate_up_proj.weight",
+                    "name": "model.layers.0.self_attn.o_proj.weight",
                     "shape": [
-                        37888,
+                        3584,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 271581184,
+                    "nbytes": 25690112,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "92a7bea5fcddf575091c43b1c4df714c"
+            "md5sum": "23278f4c2c2bd26e27c57bf98ad4ef8c"
         },
         {
             "dataPath": "params_shard_7.bin",
@@ -160,59 +160,59 @@
         {
             "dataPath": "params_shard_8.bin",
             "format": "raw-shard",
-            "nbytes": 33030144,
+            "nbytes": 271581184,
             "records": [
                 {
-                    "name": "model.layers.2.self_attn.c_attn.weight",
+                    "name": "model.layers.1.mlp.gate_up_proj.weight",
                     "shape": [
-                        4608,
+                        37888,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 33030144,
+                    "nbytes": 271581184,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "8af6d905b41911171901c0c9b1309afb"
+            "md5sum": "92a7bea5fcddf575091c43b1c4df714c"
         },
         {
             "dataPath": "params_shard_9.bin",
             "format": "raw-shard",
-            "nbytes": 25690112,
+            "nbytes": 33030144,
             "records": [
                 {
-                    "name": "model.layers.2.self_attn.o_proj.weight",
+                    "name": "model.layers.1.self_attn.c_attn.weight",
                     "shape": [
-                        3584,
+                        4608,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 25690112,
+                    "nbytes": 33030144,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "126e17f7b67d299092e34621d3d01ba5"
+            "md5sum": "c03154c2e7e28390bd1554a72a582034"
         },
         {
             "dataPath": "params_shard_10.bin",
             "format": "raw-shard",
-            "nbytes": 271581184,
+            "nbytes": 25690112,
             "records": [
                 {
-                    "name": "model.layers.2.mlp.gate_up_proj.weight",
+                    "name": "model.layers.1.self_attn.o_proj.weight",
                     "shape": [
-                        37888,
+                        3584,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 271581184,
+                    "nbytes": 25690112,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "56b5611e7e548cbe8da292871a122b53"
+            "md5sum": "d46398b81504bd2d82830108afdd8407"
         },
         {
             "dataPath": "params_shard_11.bin",
@@ -236,97 +236,97 @@
         {
             "dataPath": "params_shard_12.bin",
             "format": "raw-shard",
-            "nbytes": 33030144,
+            "nbytes": 271581184,
             "records": [
                 {
-                    "name": "model.layers.3.self_attn.c_attn.weight",
+                    "name": "model.layers.2.mlp.gate_up_proj.weight",
                     "shape": [
-                        4608,
+                        37888,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 33030144,
+                    "nbytes": 271581184,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "10c68f4a89d8c9e5ac3fd00b5ce2ee47"
+            "md5sum": "56b5611e7e548cbe8da292871a122b53"
         },
         {
             "dataPath": "params_shard_13.bin",
             "format": "raw-shard",
-            "nbytes": 25690112,
+            "nbytes": 33030144,
             "records": [
                 {
-                    "name": "model.layers.3.self_attn.o_proj.weight",
+                    "name": "model.layers.2.self_attn.c_attn.weight",
                     "shape": [
-                        3584,
+                        4608,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 25690112,
+                    "nbytes": 33030144,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "e655468aacdcefbc5172993aea2634e2"
+            "md5sum": "8af6d905b41911171901c0c9b1309afb"
         },
         {
             "dataPath": "params_shard_14.bin",
             "format": "raw-shard",
-            "nbytes": 271581184,
+            "nbytes": 25690112,
             "records": [
                 {
-                    "name": "model.layers.3.mlp.gate_up_proj.weight",
+                    "name": "model.layers.2.self_attn.o_proj.weight",
                     "shape": [
-                        37888,
+                        3584,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 271581184,
+                    "nbytes": 25690112,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "ce9430ea30508f4c11646d9f6987c7d5"
+            "md5sum": "126e17f7b67d299092e34621d3d01ba5"
         },
         {
             "dataPath": "params_shard_15.bin",
             "format": "raw-shard",
-            "nbytes": 135790592,
+            "nbytes": 33030144,
             "records": [
                 {
-                    "name": "model.layers.3.mlp.down_proj.weight",
+                    "name": "model.layers.3.self_attn.c_attn.weight",
                     "shape": [
-                        3584,
-                        18944
+                        4608,
+                        3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 135790592,
+                    "nbytes": 33030144,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "8463225b5d39d8aa6befc7e394ff9a80"
+            "md5sum": "10c68f4a89d8c9e5ac3fd00b5ce2ee47"
         },
         {
             "dataPath": "params_shard_16.bin",
             "format": "raw-shard",
-            "nbytes": 1089994752,
+            "nbytes": 25690112,
             "records": [
                 {
-                    "name": "lm_head.weight",
+                    "name": "model.layers.3.self_attn.o_proj.weight",
                     "shape": [
-                        152064,
+                        3584,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 1089994752,
+                    "nbytes": 25690112,
                     "byteOffset": 0
                 }
             ],
-            "md5sum": "edc0c39312d7ac18516c511b41a46f02"
+            "md5sum": "e655468aacdcefbc5172993aea2634e2"
         },
         {
             "dataPath": "params_shard_17.bin",
@@ -334,25 +334,34 @@
             "nbytes": 33131520,
             "records": [
                 {
-                    "name": "model.layers.0.self_attn.c_attn.weight",
+                    "name": "model.layers.3.input_layernorm.weight",
                     "shape": [
-                        4608,
                         3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 33030144,
+                    "nbytes": 7168,
                     "byteOffset": 0
                 },
                 {
-                    "name": "model.layers.0.self_attn.c_attn.bias",
+                    "name": "model.layers.3.post_attention_layernorm.weight",
                     "shape": [
-                        4608
+                        3584
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 9216,
-                    "byteOffset": 33030144
+                    "nbytes": 7168,
+                    "byteOffset": 7168
+                },
+                {
+                    "name": "model.norm.weight",
+                    "shape": [
+                        3584
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 7168,
+                    "byteOffset": 14336
                 },
                 {
                     "name": "model.layers.0.input_layernorm.weight",
@@ -362,7 +371,7 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33039360
+                    "byteOffset": 21504
                 },
                 {
                     "name": "model.layers.0.post_attention_layernorm.weight",
@@ -372,17 +381,28 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33046528
+                    "byteOffset": 28672
                 },
                 {
-                    "name": "model.layers.1.self_attn.c_attn.bias",
+                    "name": "model.layers.0.self_attn.c_attn.bias",
                     "shape": [
                         4608
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 9216,
-                    "byteOffset": 33053696
+                    "byteOffset": 35840
+                },
+                {
+                    "name": "model.layers.0.self_attn.c_attn.weight",
+                    "shape": [
+                        4608,
+                        3584
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33030144,
+                    "byteOffset": 45056
                 },
                 {
                     "name": "model.layers.1.input_layernorm.weight",
@@ -392,7 +412,7 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33062912
+                    "byteOffset": 33075200
                 },
                 {
                     "name": "model.layers.1.post_attention_layernorm.weight",
@@ -402,17 +422,17 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33070080
+                    "byteOffset": 33082368
                 },
                 {
-                    "name": "model.layers.2.self_attn.c_attn.bias",
+                    "name": "model.layers.1.self_attn.c_attn.bias",
                     "shape": [
                         4608
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 9216,
-                    "byteOffset": 33077248
+                    "byteOffset": 33089536
                 },
                 {
                     "name": "model.layers.2.input_layernorm.weight",
@@ -422,7 +442,7 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33086464
+                    "byteOffset": 33098752
                 },
                 {
                     "name": "model.layers.2.post_attention_layernorm.weight",
@@ -432,50 +452,30 @@
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 7168,
-                    "byteOffset": 33093632
+                    "byteOffset": 33105920
                 },
                 {
-                    "name": "model.layers.3.self_attn.c_attn.bias",
+                    "name": "model.layers.2.self_attn.c_attn.bias",
                     "shape": [
                         4608
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
                     "nbytes": 9216,
-                    "byteOffset": 33100800
+                    "byteOffset": 33113088
                 },
                 {
-                    "name": "model.layers.3.input_layernorm.weight",
-                    "shape": [
-                        3584
-                    ],
-                    "dtype": "float16",
-                    "format": "f32-to-bf16",
-                    "nbytes": 7168,
-                    "byteOffset": 33110016
-                },
-                {
-                    "name": "model.layers.3.post_attention_layernorm.weight",
-                    "shape": [
-                        3584
-                    ],
-                    "dtype": "float16",
-                    "format": "f32-to-bf16",
-                    "nbytes": 7168,
-                    "byteOffset": 33117184
-                },
-                {
-                    "name": "model.norm.weight",
+                    "name": "model.layers.3.self_attn.c_attn.bias",
                     "shape": [
-                        3584
+                        4608
                     ],
                     "dtype": "float16",
                     "format": "f32-to-bf16",
-                    "nbytes": 7168,
-                    "byteOffset": 33124352
+                    "nbytes": 9216,
+                    "byteOffset": 33122304
                 }
             ],
-            "md5sum": "70fbdf29d3964389bcae6e3d22e00b4c"
+            "md5sum": "8024ca13796190a329892865444cd3d9"
         }
     ]
 }

params_shard_0.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb41eaf0940118f3c87f636fa0c6f644241134077ce70ced4c4a9cf4e5ed3b4
-size 1089994752
+oid sha256:027bda185ff72d37320fa16426ab0f7c7128aab2ac9eb72d8657340e48d90e4d
+size 978345984

params_shard_1.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63265fae190fd35ce4b7952fd15222dc24e73e41176bc971d653fbe0fb182f28
-size 25690112
+oid sha256:89b4abaaa000ea810b43c6a40e7215ef23bf9774e4d533534fdef78066e023b9
+size 135790592

params_shard_10.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ac62dd8140674016640232e972f3380a5282f1044d9766d064e8fc28c314b0
-size 271581184
+oid sha256:c0db85a6033bbbb1b6e4d82705b9c21312baf17aeeb65ecf05f39efc956208eb
+size 25690112

params_shard_12.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b27adf93985b8861804b61c9ca36d86afd88dbdd1a16256a20bf0539dae8084
-size 33030144
+oid sha256:63ac62dd8140674016640232e972f3380a5282f1044d9766d064e8fc28c314b0
+size 271581184

params_shard_13.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa46bfc1cd163cbaaa7fcc46c8599c529c757c59a3235a026692034ec84a65c8
-size 25690112
+oid sha256:0e10b68357f9f8d8ea44347b78c4ddd51a120f2402b8f157d732087e37d2e993
+size 33030144

params_shard_14.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c08916833966babd12d02deefb4f0745b0f6e095a6fc08fb142e3228799cdaa
-size 271581184
+oid sha256:47cfd3df2045c382bd859dc5255ebf516b4bf8c8dc4c5453385b86e36102d9f5
+size 25690112

params_shard_15.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b4abaaa000ea810b43c6a40e7215ef23bf9774e4d533534fdef78066e023b9
-size 135790592
+oid sha256:6b27adf93985b8861804b61c9ca36d86afd88dbdd1a16256a20bf0539dae8084
+size 33030144

params_shard_16.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a25d1741800bee6c035ed1e9c9e6c08954b2d00518e9954b62f70a07df6254c
-size 1089994752
+oid sha256:fa46bfc1cd163cbaaa7fcc46c8599c529c757c59a3235a026692034ec84a65c8
+size 25690112

params_shard_17.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f0190cb193bbb1ca4d6bfe83caee79e29d4e8bcf1fbdd283c44798f73e81dbf
+oid sha256:d21c896dba637025e09d1bc08af03e6399a8c2c1e5c385aa70dd90232cfbc9c7
 size 33131520

params_shard_2.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a184d95f1ec81da8b912cc4f609c0c6dda201ee367c813d9f247aadf97d3e500
+oid sha256:8c08916833966babd12d02deefb4f0745b0f6e095a6fc08fb142e3228799cdaa
 size 271581184

params_shard_3.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e351746ffadbc023756d7247b2a8b19eb7a77bccf1a20447a8e90e8b20f2a04c
-size 135790592
+oid sha256:5fe753df73072b4952a933e0600c8e4b8cf9f2be71a6025d53ef87f54b967d64
+size 978345984

params_shard_4.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66f118bf0e88c2995e92e965c6cf745181d48c54429ab8c19cfea311eedea2c
-size 33030144
+oid sha256:e351746ffadbc023756d7247b2a8b19eb7a77bccf1a20447a8e90e8b20f2a04c
+size 135790592

params_shard_5.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0db85a6033bbbb1b6e4d82705b9c21312baf17aeeb65ecf05f39efc956208eb
-size 25690112
+oid sha256:a184d95f1ec81da8b912cc4f609c0c6dda201ee367c813d9f247aadf97d3e500
+size 271581184

params_shard_6.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f19809f0965814f1caea799976e36c80c8b0350abccc96833fe1de430322a2
-size 271581184
+oid sha256:63265fae190fd35ce4b7952fd15222dc24e73e41176bc971d653fbe0fb182f28
+size 25690112

params_shard_8.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e10b68357f9f8d8ea44347b78c4ddd51a120f2402b8f157d732087e37d2e993
-size 33030144
+oid sha256:48f19809f0965814f1caea799976e36c80c8b0350abccc96833fe1de430322a2
+size 271581184

params_shard_9.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47cfd3df2045c382bd859dc5255ebf516b4bf8c8dc4c5453385b86e36102d9f5
-size 25690112
+oid sha256:f66f118bf0e88c2995e92e965c6cf745181d48c54429ab8c19cfea311eedea2c
+size 33030144