update model weights

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.model filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -2,6 +2,7 @@
   "architectures": [
     "InternLM2ForCausalLM"
   ],
+  "attn_implementation": "eager",
   "auto_map": {
     "AutoConfig": "configuration_internlm2.InternLM2Config",
     "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
@@ -21,14 +22,11 @@
   "num_key_value_heads": 8,
   "pad_token_id": 2,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 2.0,
-    "type": "dynamic"
-  },
+  "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.37.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
   "use_cache": true,
   "vocab_size": 92544
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.37.0.dev0"
-}
+  "transformers_version": "4.37.1"
+}

model.safetensors → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ae274b07d799b5411f1a1f5d2cd86ba0e8bcc54347eab07301602f2be68b70
-size 3778239296
+oid sha256:1c84d51a82013b4b657eaf5c4c3d78a45e4545b2c001de9e60460381dedcfa7c
+size 1981392632

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9263b900177553706ba9a5b9ef0a370e8c48cc8f6363e8dc4b2f7ca332d326c
+size 1796846560

model.safetensors.index.json

@@ -0,0 +1,178 @@
+{
+  "metadata": {
+    "total_size": 3778220032
+  },
+  "weight_map": {
+    "model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00002.safetensors",
+    "output.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -1,6 +1,38 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,17 +1,6 @@
 {
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_internlm2.InternLM2Tokenizer",
-      "tokenization_internlm2_fast.InternLM2TokenizerFast"
-    ]
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "tokenizer_class": "InternLM2Tokenizer",
-  "unk_token": "<unk>",
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -37,48 +26,48 @@
       "single_word": false,
       "special": true
     },
-    "92543": {
-      "content": "<|im_start|>",
+    "92538": {
+      "content": "<|plugin|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92542": {
-      "content": "<|im_end|>",
+    "92539": {
+      "content": "<|interpreter|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92541": {
-      "content": "<|action_start|>",
+    "92540": {
+      "content": "<|action_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92540": {
-      "content": "<|action_end|>",
+    "92541": {
+      "content": "<|action_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92539": {
-      "content": "<|interpreter|>",
+    "92542": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92538": {
-      "content": "<|plugin|>",
+    "92543": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -86,5 +75,28 @@
       "special": true
     }
   },
-  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
-}
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_internlm2.InternLM2Tokenizer",
+      "tokenization_internlm2_fast.InternLM2TokenizerFast"
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "decode_with_prefix_space": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": null,
+  "tokenizer_class": "InternLM2Tokenizer",
+  "unk_token": "<unk>"
+}