Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +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 %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.5.4",
+  "use_cache": true,
+  "vocab_size": 49153
+}

config.snapshot.json

@@ -0,0 +1,36 @@
+{
+  "model_name": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "dataset_path": "your_dataset_path_here",
+  "dataset_mode": "full",
+  "platform": "gpu",
+  "wanb_project": "convfill",
+  "training_split_percent": 0.9,
+  "add_special_tokens": true,
+  "special_tokens": {
+    "additional_special_tokens": [
+      "<sil>"
+    ]
+  },
+  "boundary_tokens": {
+    "USER_START": "<|im_start|>user\n",
+    "KNOWLEDGE_START": "<|im_start|>knowledge\n",
+    "ASSN_START": "<|im_start|>assistant\n",
+    "END": "<|im_end|>\n"
+  },
+  "training_config": {
+    "batch_size": 4,
+    "accumulate_grad_batches": 4,
+    "num_epochs": 1,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.01,
+    "warmup_steps": 200,
+    "scheduler": "cosine",
+    "val_check_interval": 0.25
+  },
+  "logging_config": {
+    "log_every_n_steps": 10
+  },
+  "checkpoint_config": {
+    "every_n_train_steps": 50
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77219a917ed0e409447541d8397f02b7dc9f5919b41c43fc6c9bf8ddcb080a25
+size 723676832

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<sil>"
+  ],
+  "is_local": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}