Fix config _name_or_path to openbmb/MiniCPM5-1B-Base

.ms_upload_cache

@@ -0,0 +1 @@
+{"version": 3, "repo_id": "OpenBMB/MiniCPM5-1B-Base", "files": {"generation_config.json|1779430314.6357388|154": {"hash": "697492a10461be0941f853bbeb6d2d3696361d3063a8427365c30c2b56faedda", "size": 154, "status": "c"}, "config.json|1779430321.8935978|729": {"hash": "b0d42a6ec2ec199d5a0f4a641c6ca1f3c69baef37ae5057d64c6e6133063d4a5", "size": 729, "status": "c"}, "chat_template.jinja|1774421588.0|9060": {"hash": "865063bd21a7fa5bc5921afb979bcd7ae6926229e7eed7235a8bf97040e6573c", "size": 9060, "status": "c"}, "model.safetensors.index.json|1779430321.9679534|18004": {"hash": "1b2eaa65742b9cadec7a95d65d8533208d6294b1952ee3450af30b6aa4b3f298", "size": 18004, "status": "c"}, "model-00000-of-00001.safetensors|1779430321.84895|2161290944": {"hash": "bcf629379a6f5f5e18e9ec637a0e054de7f14e311a66b3d9b0932d06ec487f0e", "size": 2161290944, "status": "c"}, "special_tokens_map.json|1774421588.0|551": {"hash": "82d96d7a9e6ced037f12394b7ea6a5b02e6ca87e0d11edaa8d60d9be857ce7db", "size": 551, "status": "c"}, "tokenizer.json|1774421588.0|9894271": {"hash": "3e065a558a034185fe299917b398685c1facd0169a9eea1e629eb30c171fed81", "size": 9894271, "status": "c"}, "tokenizer_config.json|1779430321.8939757|94416": {"hash": "094efb3cf1ff412284cc5945fc99dff58673a912760d04483a04aa1c716f66fd", "size": 94416, "status": "c"}, "config.json|1779509027.7074554|728": {"hash": "7f8a06a1be724b8d922780d5b0742be4adfe628f8989c66aec4499bb78dff9ce", "size": 728, "status": "c"}, "generation_config.json|1779516522.3891585|153": {"hash": "a418639700a3026691aaa8c4ee4a38a83f380c6d24164a8fdd60a29af80b4fcd", "size": 153, "status": "c"}, "config.json|1779595241.5010943|731": {"hash": "f6a54013efd621f26dbe94f7258445bfbf587cd323b5f6f2411d22dcecc4ef7d", "size": 731, "status": "c"}}}

config.json

@@ -1,5 +1,5 @@
 {
-    "_name_or_path": "openbmb/MiniCPM5-0.9B",
+    "_name_or_path": "openbmb/MiniCPM5-1B-Base",
     "architectures": [
         "LlamaForCausalLM"
     ],

model-00000-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf629379a6f5f5e18e9ec637a0e054de7f14e311a66b3d9b0932d06ec487f0e
+size 2161290944

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 2161265664
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00000-of-00001.safetensors",
+    "model.embed_tokens.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.norm.weight": "model-00000-of-00001.safetensors"
+  }
+}