step 5000

config.json

@@ -4,26 +4,26 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 64,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 32,
+  "num_attention_heads": 16,
   "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
+  "num_key_value_heads": 16,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 130000.0,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 49152
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d5f8033be65412cc69db9a4fce2ad44b508c1f168d6a321ac8462beda32d7f
-size 2348962288
+oid sha256:34c72844de97f4bd5082979fe5c9d12754f64bb1c48355d80b9b4737ef965e19
+size 2409779720

special_tokens_map.json

@@ -1,41 +1,29 @@
 {
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
-  ],
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d27c493c729a66ecefc837280b05d948b1ed50d130eebdbf911b1b36cf38ed7
-size 3522656
+oid sha256:97f6fd3d989a1881bc04be77ed29a074bbdc7fa2c3bf57410a47c94bff14c422
+size 3619013

tokenizer_config.json

@@ -1,167 +1,41 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<|im_start|>",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "<|im_end|>",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<repo_name>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<reponame>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<file_sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<filename>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<gh_stars>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<issue_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<issue_comment>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<issue_closed>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<jupyter_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<jupyter_text>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<jupyter_code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
-      "content": "<jupyter_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "15": {
-      "content": "<jupyter_script>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<empty_output>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
-  ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 8192,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
-  "vocab_size": 49152
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }