Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{{ '<s>system\n' + system_message + '</s>\n' }}{% else %}{{ '<s>system\nYou are MiniMind, a helpful AI assistant.</s>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<s>user\n' + content + '</s>\n<s>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "TransformerLM"
+  ],
+  "aux_loss_alpha": 0.1,
+  "dim": 512,
+  "dropout": 0.0,
+  "flash_attn": true,
+  "hidden_dim": 1408,
+  "max_seq_len": 1024,
+  "model_type": "transformerlm",
+  "multiple_of": 64,
+  "n_heads": 8,
+  "n_kv_heads": 2,
+  "n_layers": 8,
+  "n_routed_experts": 4,
+  "n_shared_experts": true,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_experts_per_tok": 2,
+  "rope_theta": 1000000.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 6400
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaaa6389e5c6d7c7e8db6a372ecf63b51ff7386fecb800b004aa027ca9aa095
+size 103344412

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec2208bfa4e8cdad702cc5152373a98d6ef577bebebe8d5507e1b36850cf4c2
+size 116434248

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dce3a6614de721ef4246c5dec1671b0caff16def8e89db02a4d5b68ccc8a40
+size 116451407

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "<unk>"
+}