Upload model

config.json

@@ -1,32 +1,32 @@
 {
-  "_name_or_path": "data/bigdata_2",
-  "architectures": [
-    "StableLmForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
-  "hidden_act": "silu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 5632,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 4096,
-  "model_type": "stablelm",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 32,
-  "pad_token_id": 100257,
-  "partial_rotary_factor": 0.25,
-  "qk_layernorm": false,
-  "rope_scaling": null,
-  "rope_theta": 10000,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.2",
-  "use_cache": false,
-  "use_parallel_residual": false,
-  "use_qkv_bias": true,
-  "vocab_size": 100352
-}
+    "_name_or_path": "merge23",
+    "architectures": [
+        "StableLmForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 100257,
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 4096,
+    "model_type": "stablelm",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 32,
+    "pad_token_id": 100257,
+    "partial_rotary_factor": 0.25,
+    "qk_layernorm": false,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.40.2",
+    "use_cache": false,
+    "use_parallel_residual": false,
+    "use_qkv_bias": true,
+    "vocab_size": 100352
+}

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 100257,
   "do_sample": true,
   "eos_token_id": 100257,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.41.2"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be612b5e7b636f460533f3bad9c2cf8ad5ea8debae511badd4564aa37626943
-size 981631656
+oid sha256:2933e0c010a75032b7db70bcc00c1c64cd5ee1590840bd1eecf97c2300fdfe5c
+size 1963254496

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bdc07ec34dcae126868b74797e5e427c8f3fde16dedd73e8650256a9f782fe
-size 996449440
+oid sha256:e7838e203d4983ec3d97ac38c0c4ac9841be546a1806da245fb987f4c0491b9d
+size 1992883384

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e7e56f6af8e58ccd58c421396ff06952f5d3b852b8347e4a36a75536f9246f
-size 899945896
+oid sha256:2c91a2c2f357e8f74a04e47dba2edad7cc5e94cf63afd5b8c268f06554839eb3
+size 1799878064

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31b54b8f8deb4d4d4b50f67e0f70de1e49beec2fff11e95f308fa6ab6588701
-size 411041920
+oid sha256:25ecf0759898dcf0a584c34f1151b1616a0dcd185685ef601d69873f2f56776f
+size 822083712

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 3289030656
+    "total_size": 6578061312
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 3896,
+    "max_length": 3696,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 3896
+      "Fixed": 3696
     },
     "direction": "Left",
     "pad_to_multiple_of": null,
@@ -350,6 +350,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "100256": {
@@ -304,9 +305,15 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 3896,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }