Upload fine-tuned CodeMind model

checkpoints/checkpoint-94/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: codellama/CodeLlama-7b-hf
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:codellama/CodeLlama-7b-hf
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
 - lora
 - transformers
 ---
@@ -204,4 +204,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
+- PEFT 0.17.1
 - PEFT 0.17.0

checkpoints/checkpoint-94/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,

checkpoints/checkpoint-94/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ad631c5d6c6d209ebd70a23c865e4b110c827017f205b18a2432ebbc554f3f
-size 16794200
+oid sha256:a8f402414502e7546231249c382c071c163a58eec09838b31328d00db17f99cf
+size 4517152

checkpoints/checkpoint-94/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoints/checkpoint-94/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee59e677a224318171cc166414866e279b0dd120f4ca041953190e49dd4e0372
-size 33662074
+oid sha256:ef61894ea730991e33f2cce894aeac277458a3e3daab7ae2de9a95f69606b3d2
+size 9087051

checkpoints/checkpoint-94/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3614fc15a38e35eb840809f67f4861938ac6b348a9177a9d9742a1d9d167a7cf
-size 14244
+oid sha256:3ebc6a66c38d82fae596405cd59f9b05aa195310c5e9d92a33a3e411244cc412
+size 14645

checkpoints/checkpoint-94/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c727a1fa2ac82030a89dbe95e299a001ac7f361424036928750e97c017c4da6
-size 988
+oid sha256:ef04b50f717ccc1fb7d4248cbebe9f0c3884cadeb50b356efd9000eb189709aa
+size 1383

checkpoints/checkpoint-94/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cfd2d7ed5d052f6462cd13ac4e880e53bdfba79dce5db3e0ff53064d3a3eb5
-size 1064
+oid sha256:f1053ab1e5d956431f3cae8a79e6dea26044c5acb288eb4cff4437e289c20048
+size 1465

checkpoints/checkpoint-94/special_tokens_map.json

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

checkpoints/checkpoint-94/tokenizer.json

@@ -10,7 +10,7 @@
     "strategy": {
       "Fixed": 512
     },
-    "direction": "Left",
+    "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 2,
     "pad_type_id": 0,
@@ -43,42 +43,6 @@
       "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": {
@@ -32185,23 +32149,7 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "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
+      "给": 31999
     },
     "merges": [
       [
@@ -277199,50 +277147,6 @@
       [
         "▁",
         "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
-      ],
-      [
-        "▁<",
-        "SU"
-      ],
-      [
-        "▁<SU",
-        "F"
-      ],
-      [
-        "▁<",
-        "PRE"
-      ],
-      [
-        "▁<",
-        "M"
-      ],
-      [
-        "▁<M",
-        "ID"
-      ],
-      [
-        "▁<",
-        "E"
-      ],
-      [
-        "▁<E",
-        "OT"
-      ],
-      [
-        "▁<PRE",
-        ">"
-      ],
-      [
-        "▁<SUF",
-        ">"
-      ],
-      [
-        "▁<MID",
-        ">"
-      ],
-      [
-        "▁<EOT",
-        ">"
       ]
     ]
   }

checkpoints/checkpoint-94/tokenizer.model

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

checkpoints/checkpoint-94/tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,60 +26,18 @@
       "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>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
   "extra_special_tokens": {},
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": false,
+  "model_max_length": 2048,
   "pad_token": "</s>",
-  "prefix_token": "▁<PRE>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "CodeLlamaTokenizer",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

checkpoints/checkpoint-94/trainer_state.json

@@ -11,30 +11,30 @@
   "log_history": [
     {
       "epoch": 0.42780748663101603,
-      "grad_norm": 0.17147783935070038,
+      "grad_norm": 5.215646743774414,
       "learning_rate": 0.00015957446808510637,
-      "loss": 12.7183,
+      "loss": 6.4825,
       "step": 20
     },
     {
       "epoch": 0.8556149732620321,
-      "grad_norm": 0.10348663479089737,
+      "grad_norm": 0.32128605246543884,
       "learning_rate": 0.00011702127659574468,
-      "loss": 12.9983,
+      "loss": 0.3244,
       "step": 40
     },
     {
       "epoch": 1.2780748663101604,
-      "grad_norm": 0.07714056968688965,
+      "grad_norm": 0.23809807002544403,
       "learning_rate": 7.446808510638298e-05,
-      "loss": 12.7687,
+      "loss": 0.2467,
       "step": 60
     },
     {
       "epoch": 1.7058823529411766,
-      "grad_norm": 0.09477601200342178,
+      "grad_norm": 0.2185528576374054,
       "learning_rate": 3.191489361702128e-05,
-      "loss": 12.7049,
+      "loss": 0.2283,
       "step": 80
     }
   ],
@@ -55,7 +55,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5192512670990336e+16,
+  "total_flos": 2379748793647104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoints/checkpoint-94/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5668cf3ad716b632c2239a3e191b3db8db0d2224ecfa266312785c95ce7e77a
-size 5368
+oid sha256:4a0a2a708a75961ab713089d6d62ba16b5b57b846e10dcd4ca4a7b443e0d86af
+size 5777

final_adapter/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: codellama/CodeLlama-7b-hf
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:codellama/CodeLlama-7b-hf
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
 - lora
 - transformers
 ---

final_adapter/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

final_adapter/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ad631c5d6c6d209ebd70a23c865e4b110c827017f205b18a2432ebbc554f3f
-size 16794200
+oid sha256:a8f402414502e7546231249c382c071c163a58eec09838b31328d00db17f99cf
+size 4517152

final_adapter/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

final_adapter/special_tokens_map.json

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

final_adapter/tokenizer.json

@@ -10,7 +10,7 @@
     "strategy": {
       "Fixed": 512
     },
-    "direction": "Left",
+    "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 2,
     "pad_type_id": 0,
@@ -43,42 +43,6 @@
       "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": {
@@ -32185,23 +32149,7 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "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
+      "给": 31999
     },
     "merges": [
       [
@@ -277199,50 +277147,6 @@
       [
         "▁",
         "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
-      ],
-      [
-        "▁<",
-        "SU"
-      ],
-      [
-        "▁<SU",
-        "F"
-      ],
-      [
-        "▁<",
-        "PRE"
-      ],
-      [
-        "▁<",
-        "M"
-      ],
-      [
-        "▁<M",
-        "ID"
-      ],
-      [
-        "▁<",
-        "E"
-      ],
-      [
-        "▁<E",
-        "OT"
-      ],
-      [
-        "▁<PRE",
-        ">"
-      ],
-      [
-        "▁<SUF",
-        ">"
-      ],
-      [
-        "▁<MID",
-        ">"
-      ],
-      [
-        "▁<EOT",
-        ">"
       ]
     ]
   }

final_adapter/tokenizer.model

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

final_adapter/tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,60 +26,18 @@
       "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>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
   "extra_special_tokens": {},
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": false,
+  "model_max_length": 2048,
   "pad_token": "</s>",
-  "prefix_token": "▁<PRE>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "CodeLlamaTokenizer",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }