Initial upload of 3.94MB tiny-random MiniCPM

.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

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openbmb/MiniCPM-2B-sft-bf16",
   "architectures": [
     "MiniCPMForCausalLM"
   ],
@@ -16,22 +15,22 @@
   "dim_model_base": 256,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 32,
+  "hidden_size": 24,
   "initializer_range": 0.1,
   "intermediate_size": 64,
   "max_position_embeddings": 4096,
   "model_type": "minicpm",
-  "num_attention_heads": 2,
+  "num_attention_heads": 4,
   "num_hidden_layers": 1,
-  "num_key_value_heads": 1,
+  "num_key_value_heads": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "scale_depth": 1.4,
   "scale_emb": 12,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 122753
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ebd7a91fae82eef06ce0792b66a3c80b05db26f0d8a9279ac0b9ea22549664
-size 4134408
+oid sha256:92516be6f204b99a01d57af64f96c6ca67b7e7281e2cc738c21d5b51ee583ebc
+size 5906128

special_tokens_map.json

@@ -2,21 +2,21 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:c9aafcd7da1f5611dab6be545db74d5552a2ccc9c2a12c72ea7be63aac4a25d7
+size 1994871

tokenizer_config.json

@@ -6,7 +6,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -14,7 +14,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,20 +22,22 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'] + '<AI>'}}{% else %}{{message['content']}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "legacy": true,
-  "model_max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false