Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -8,14 +8,14 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 5120,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 16384,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -33,10 +33,10 @@
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.38.2",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32016
 }

generation_config.json

@@ -1,10 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "max_length": 4096,
-  "pad_token_id": 0,
-  "temperature": 0.6,
-  "top_p": 0.9,
   "transformers_version": "4.38.2"
 }

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8c0ae9cd517ee4a0feeee0886a3e5f90ebee6ff7285977bd0340c4956f6875
+size 5000268830

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d4212eb7bbb0eaae609e9507e036efa2414e4ecb7b7f6e1ccd324ee2660723
+size 2202469569

special_tokens_map.json

@@ -1,4 +1,10 @@
 {
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -13,6 +19,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "</s>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -29,6 +43,42 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32007,
+      "content": "▁<PRE>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32008,
+      "content": "▁<SUF>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32009,
+      "content": "▁<MID>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32010,
+      "content": "▁<EOT>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -32134,7 +32184,23 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "给": 31999
+      "给": 31999,
+      "▁<SU": 32000,
+      "▁<SUF": 32001,
+      "▁<PRE": 32002,
+      "▁<M": 32003,
+      "▁<MID": 32004,
+      "▁<E": 32005,
+      "▁<EOT": 32006,
+      "▁<PRE>": 32007,
+      "▁<SUF>": 32008,
+      "▁<MID>": 32009,
+      "▁<EOT>": 32010,
+      "▁<EOT><EOT>": 32011,
+      "▁<EOT><EOT><EOT>": 32012,
+      "▁<EOT><EOT><EOT><EOT>": 32013,
+      "▁<EOT><EOT><EOT><EOT><EOT>": 32014,
+      "▁<EOT><EOT><EOT><EOT><EOT><EOT>": 32015
     },
     "merges": [
       "▁ t",
@@ -93385,7 +93451,18 @@
       "▁▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁▁▁▁▁ ▁▁▁▁",
-      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "▁< SU",
+      "▁<SU F",
+      "▁< PRE",
+      "▁< M",
+      "▁<M ID",
+      "▁< E",
+      "▁<E OT",
+      "▁<PRE >",
+      "▁<SUF >",
+      "▁<MID >",
+      "▁<EOT >"
     ]
   }
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -25,17 +25,60 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
   "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 | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "padding_side": "right",
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }