End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: KayO/SmolLM2-FT-MyDataset-WithChatTemplate
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
 library_name: transformers
 model_name: SmolLM2-FT-DPO
 tags:
@@ -13,7 +13,7 @@ licence: license
 
 # Model Card for SmolLM2-FT-DPO
 
-This model is a fine-tuned version of [KayO/SmolLM2-FT-MyDataset-WithChatTemplate](https://huggingface.co/KayO/SmolLM2-FT-MyDataset-WithChatTemplate).
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "KayO/SmolLM2-FT-MyDataset-WithChatTemplate",
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,6 +27,12 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
   "transformers_version": "4.46.3",
   "use_cache": false,
   "vocab_size": 49152

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4064d60fd89a9ad885ea9ee44c9d72d4ee5b9bf47fd3008bb3f4c30adbcb8aab
+oid sha256:313088167930aaa341d64283f97ecaf42e0d7e54af14d5677a8e185a08217b3f
 size 538090408

tokenizer_config.json

@@ -143,7 +143,7 @@
     "<|im_end|>"
   ],
   "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "model_max_length": 8192,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f17783bb256c0758604e2894a1875d3084251c561d55d0bb0498299d33aa1b
+oid sha256:f5a199b7ac2de43e8ca2400cfc7304bd9af3563738f45c44c7a92bfd58ef10b6
 size 6072