Update subtitle postprocessor fine-tuned model

README.md

@@ -1,6 +1,13 @@
 ---
-library_name: transformers
-tags: []
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- transformers
+- trl
 ---
 
 # Model Card for Model ID
@@ -15,7 +22,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +203,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter_config.json

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "gate_proj",
+    "o_proj",
     "k_proj",
-    "up_proj",
     "down_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c4bf4593d60359e1421ca80d2b94aba0ef75beb45c74978bed1c50dcfa7111
+oid sha256:455ae313667c729be9d4eb44d665834ed5a1088ad87b7f5fda757857a7f9453e
 size 19593064

chat_template.jinja

@@ -1,6 +1,6 @@
 {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
 You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
-' }}{% endif %}{{'<|im_start|>' + message['role'] + '
-' + message['content'] + '<|im_end|>' + '
-'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}{{ '<|im_start|>' + message['role'] + '
+' }}{% if message['role'] == 'assistant' %}{% generation %}{{ message['content'] }}{% endgeneration %}{% else %}{{ message['content'] }}{% endif %}{{ '<|im_end|>
+' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
 ' }}{% endif %}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -159,37 +159,21 @@
   ],
   "normalizer": null,
   "pre_tokenizer": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
-  },
-  "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
+    "type": "Sequence",
+    "pretokenizers": [
       {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
+        "type": "Digits",
+        "individual_digits": true
       },
       {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
+        "type": "ByteLevel",
+        "add_prefix_space": false,
+        "trim_offsets": true,
+        "use_regex": true
       }
-    ],
-    "special_tokens": {}
+    ]
   },
+  "post_processor": null,
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
@@ -200,8 +184,8 @@
     "type": "BPE",
     "dropout": null,
     "unk_token": null,
-    "continuing_subword_prefix": "",
-    "end_of_word_suffix": "",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
     "ignore_merges": false,

tokenizer_config.json

@@ -1,16 +1,151 @@
 {
   "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": "<|im_start|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": [
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "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,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "is_local": false,
-  "local_files_only": false,
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5bc73070a4694ced65d8556f33cc194bd42f217765fe591da87caf7e93210d
+size 6353