update model weights

.gitattributes

@@ -42,3 +42,11 @@ pytorch_model-00003-of-00008.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00004-of-00008.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00005-of-00008.bin filter=lfs diff=lfs merge=lfs -text
 tokenizer.model filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00008.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": "4.33.2",
+  "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": "4.33.2"
+  "transformers_version": "4.37.1"
 }

pytorch_model-00001-of-00008.bin → model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86047ba5d0040e1db8c9c84714cb011e0a80c0bda964d075645023c0ab2a122e
-size 1949342053
+oid sha256:fd3794fc730ddd471282831ab4915aa8f9251a396e0ad64bbcb602b96e95c0c2
+size 1949337704

pytorch_model-00002-of-00008.bin → model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a465fa8d3469648864b3804e8ed571968c4effadcbe8cd497d0310c649ff718
-size 1946249825
+oid sha256:46600c6686697efe4234e907dc756670e18a9ddc95f9061c73eab90bcf28eb3e
+size 1946242696

pytorch_model-00003-of-00008.bin → model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070651dfa2c7002a76bece9053b362d5212c190afd3b636e653b2a02aa441443
-size 1979786923
+oid sha256:8d53d767ea6fb3cb6ae3b44b93e145fa99074339845cd50293fc89f4b2f4961a
+size 1979780440

pytorch_model-00004-of-00008.bin → model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b697e82ec70fd82fc8b444952033c1d80b12b735c2a54ed4bd615e5f1d14a535
-size 1946249889
+oid sha256:f2b6ae6bde2bce37e90b9b9c6e087e3b920e84024be9a6ac52b3e17e18702665
+size 1946242728

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18af6a7eaa32dd491be8fa43d0c038a6a80fc662fd67f9e5d67b2f71c809ada9
+size 1979780456

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f715e4262c12ab0f5473b31a300f5c49dcf41ec5e1471d9da3d67a4eb5b1770
+size 1946242728

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92caa2b51c815faf6092a203221368fea6e6890f8c04b30a7dee463f917ac054
+size 1979780456

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023b3d18868b5d41d96b7ba1a50348dbf58369caed88db53bdabdbc9e9155aef
+size 1748035640

model.safetensors.index.json

@@ -0,0 +1,234 @@
+{
+  "metadata": {
+    "total_size": 15475417088
+  },
+  "weight_map": {
+    "model.layers.0.attention.wo.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.attention.wqkv.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.feed_forward.w2.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.attention.wo.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.attention.wqkv.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.feed_forward.w2.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.attention.wo.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.attention.wqkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.attention.wo.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.attention.wqkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.attention.wo.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.attention.wqkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.attention.wo.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.attention.wqkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.attention.wo.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.attention.wqkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.attention.wo.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.attention.wqkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.feed_forward.w1.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.feed_forward.w2.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.attention.wo.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.attention.wqkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.attention.wo.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.attention.wqkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.attention.wo.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.attention.wqkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.attention.wo.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.attention.wqkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.feed_forward.w2.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.2.attention.wo.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.attention.wqkv.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.feed_forward.w1.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.20.attention.wo.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.attention.wqkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.feed_forward.w1.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.attention.wo.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.attention.wqkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.attention.wo.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.attention.wqkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.attention.wo.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.attention.wqkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.attention.wo.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.attention.wqkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.attention_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.feed_forward.w1.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.feed_forward.w2.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.feed_forward.w3.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.ffn_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.attention.wo.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.attention.wqkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.attention_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.ffn_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.attention.wo.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.attention.wqkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.attention_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.ffn_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.attention.wo.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.attention.wqkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.attention_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.ffn_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.attention.wo.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.attention.wqkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.attention_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.feed_forward.w2.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.ffn_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.attention.wo.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.attention.wqkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.attention_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.feed_forward.w1.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.feed_forward.w3.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.ffn_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.3.attention.wo.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.attention.wqkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.30.attention.wo.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.attention.wqkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.attention_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.feed_forward.w1.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.feed_forward.w3.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.ffn_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.attention.wo.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.attention.wqkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.attention_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.feed_forward.w1.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.feed_forward.w2.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.feed_forward.w3.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.ffn_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.4.attention.wo.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.attention.wqkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.attention.wo.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.attention.wqkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.attention.wo.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.attention.wqkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.feed_forward.w1.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.feed_forward.w2.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.attention.wo.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.attention.wqkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.attention.wo.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.attention.wqkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.attention.wo.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.attention.wqkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.feed_forward.w1.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.feed_forward.w2.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00003-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00008.safetensors",
+    "output.weight": "model-00008-of-00008.safetensors"
+  }
+}

pytorch_model-00005-of-00008.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c4d3bc6256ce4a3784940548316f8166011ca2af121bb657ea7c05d6deddba65
-size 1979786987

pytorch_model-00006-of-00008.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d6fd9ee55f7d9044e5c619a714548ae9823af3a93b5e528e0627457cffd77768
-size 1946249889

pytorch_model-00007-of-00008.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aebe5a5e12bdc2153c39d03ce6837ade6dca15eb3987600f784cb1f3a4206c39
-size 1979786987

pytorch_model-00008-of-00008.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bb6b2cf4edb4e18aa477adb422837d0a74b9a2ec2a0c48b40fac7c177505a17
-size 1748039973

pytorch_model.bin.index.json

@@ -1,234 +0,0 @@
-{
-  "metadata": {
-    "total_size": 15475417088
-  },
-  "weight_map": {
-    "model.layers.0.attention.wo.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.attention.wqkv.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.attention_norm.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.feed_forward.w1.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.feed_forward.w2.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.feed_forward.w3.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.0.ffn_norm.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.attention.wo.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.attention.wqkv.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.attention_norm.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.feed_forward.w1.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.feed_forward.w2.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.feed_forward.w3.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.1.ffn_norm.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.10.attention.wo.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.attention.wqkv.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.attention_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.feed_forward.w1.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.feed_forward.w2.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.feed_forward.w3.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.10.ffn_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.11.attention.wo.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.11.attention.wqkv.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.11.attention_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.11.feed_forward.w1.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.11.feed_forward.w2.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.11.feed_forward.w3.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.11.ffn_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.attention.wo.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.attention.wqkv.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.attention_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.feed_forward.w1.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.feed_forward.w2.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.feed_forward.w3.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.12.ffn_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.attention.wo.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.attention.wqkv.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.attention_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.feed_forward.w1.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.feed_forward.w2.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.feed_forward.w3.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.13.ffn_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.attention.wo.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.attention.wqkv.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.attention_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.feed_forward.w1.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.feed_forward.w2.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.feed_forward.w3.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.14.ffn_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.attention.wo.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.attention.wqkv.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.attention_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.feed_forward.w1.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.feed_forward.w2.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.feed_forward.w3.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.15.ffn_norm.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.16.attention.wo.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.16.attention.wqkv.weight": "pytorch_model-00004-of-00008.bin",
-    "model.layers.16.attention_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.16.feed_forward.w1.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.16.feed_forward.w2.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.16.feed_forward.w3.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.16.ffn_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.attention.wo.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.attention.wqkv.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.attention_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.feed_forward.w1.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.feed_forward.w2.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.feed_forward.w3.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.17.ffn_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.attention.wo.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.attention.wqkv.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.attention_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.feed_forward.w1.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.feed_forward.w2.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.feed_forward.w3.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.18.ffn_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.attention.wo.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.attention.wqkv.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.attention_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.feed_forward.w1.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.feed_forward.w2.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.feed_forward.w3.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.19.ffn_norm.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.2.attention.wo.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.2.attention.wqkv.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.2.attention_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.2.feed_forward.w1.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.2.feed_forward.w2.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.2.feed_forward.w3.weight": "pytorch_model-00001-of-00008.bin",
-    "model.layers.2.ffn_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.20.attention.wo.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.20.attention.wqkv.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.20.attention_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.20.feed_forward.w1.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.20.feed_forward.w2.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.20.feed_forward.w3.weight": "pytorch_model-00005-of-00008.bin",
-    "model.layers.20.ffn_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.attention.wo.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.attention.wqkv.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.attention_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.feed_forward.w1.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.feed_forward.w2.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.feed_forward.w3.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.21.ffn_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.attention.wo.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.attention.wqkv.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.attention_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.feed_forward.w1.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.feed_forward.w2.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.feed_forward.w3.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.22.ffn_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.attention.wo.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.attention.wqkv.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.attention_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.feed_forward.w1.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.feed_forward.w2.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.feed_forward.w3.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.23.ffn_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.attention.wo.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.attention.wqkv.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.attention_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.feed_forward.w1.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.feed_forward.w2.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.feed_forward.w3.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.24.ffn_norm.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.25.attention.wo.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.25.attention.wqkv.weight": "pytorch_model-00006-of-00008.bin",
-    "model.layers.25.attention_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.25.feed_forward.w1.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.25.feed_forward.w2.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.25.feed_forward.w3.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.25.ffn_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.attention.wo.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.attention.wqkv.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.attention_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.feed_forward.w1.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.feed_forward.w2.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.feed_forward.w3.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.26.ffn_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.attention.wo.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.attention.wqkv.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.attention_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.feed_forward.w1.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.feed_forward.w2.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.feed_forward.w3.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.27.ffn_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.attention.wo.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.attention.wqkv.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.attention_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.feed_forward.w1.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.feed_forward.w2.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.feed_forward.w3.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.28.ffn_norm.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.29.attention.wo.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.29.attention.wqkv.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.29.attention_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.29.feed_forward.w1.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.29.feed_forward.w2.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.29.feed_forward.w3.weight": "pytorch_model-00007-of-00008.bin",
-    "model.layers.29.ffn_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.3.attention.wo.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.attention.wqkv.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.attention_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.feed_forward.w1.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.feed_forward.w2.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.feed_forward.w3.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.3.ffn_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.30.attention.wo.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.attention.wqkv.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.attention_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.feed_forward.w1.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.feed_forward.w2.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.feed_forward.w3.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.30.ffn_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.attention.wo.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.attention.wqkv.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.attention_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.feed_forward.w1.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.feed_forward.w2.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.feed_forward.w3.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.31.ffn_norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.layers.4.attention.wo.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.attention.wqkv.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.attention_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.feed_forward.w1.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.feed_forward.w2.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.feed_forward.w3.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.4.ffn_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.attention.wo.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.attention.wqkv.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.attention_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.feed_forward.w1.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.feed_forward.w2.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.feed_forward.w3.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.5.ffn_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.attention.wo.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.attention.wqkv.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.attention_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.feed_forward.w1.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.feed_forward.w2.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.feed_forward.w3.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.6.ffn_norm.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.7.attention.wo.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.7.attention.wqkv.weight": "pytorch_model-00002-of-00008.bin",
-    "model.layers.7.attention_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.7.feed_forward.w1.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.7.feed_forward.w2.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.7.feed_forward.w3.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.7.ffn_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.attention.wo.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.attention.wqkv.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.attention_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.feed_forward.w1.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.feed_forward.w2.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.feed_forward.w3.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.8.ffn_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.attention.wo.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.attention.wqkv.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.attention_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.feed_forward.w1.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.feed_forward.w2.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.feed_forward.w3.weight": "pytorch_model-00003-of-00008.bin",
-    "model.layers.9.ffn_norm.weight": "pytorch_model-00003-of-00008.bin",
-    "model.norm.weight": "pytorch_model-00008-of-00008.bin",
-    "model.tok_embeddings.weight": "pytorch_model-00001-of-00008.bin",
-    "output.weight": "pytorch_model-00008-of-00008.bin"
-  }
-}

special_tokens_map.json

@@ -7,8 +7,32 @@
     "<|interpreter|>",
     "<|plugin|>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "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
+  }
 }

tokenization_internlm2_fast.py

@@ -56,14 +56,14 @@ class InternLM2Converter(SpmConverter):
         return unk_id
 
     def decoder(self, replacement, add_prefix_space):
-        decoders_sequence = [
-            decoders.Replace("▁", " "),
-            decoders.ByteFallback(),
-            decoders.Fuse(),
-        ]
-        if self.proto.normalizer_spec.add_dummy_prefix:
-            decoders_sequence.append(decoders.Strip(content=" ", left=1))
-        return decoders.Sequence(decoders_sequence)
+        return decoders.Sequence(
+            [
+                decoders.Replace("▁", " "),
+                decoders.ByteFallback(),
+                decoders.Fuse(),
+                decoders.Strip(content=" ", left=1),
+            ]
+        )
 
     def tokenizer(self, proto):
         model_type = proto.trainer_spec.model_type

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,
@@ -94,5 +83,20 @@
     "<|interpreter|>",
     "<|plugin|>"
   ],
-  "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 %}"
-}
+  "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>"
+}