From 3d7927b0f65741a1a408a53743eb4a645bf238cf Mon Sep 17 00:00:00 2001
From: GeneZC <zhangchen3@xiaohongshu.com>
Date: Tue, 14 Nov 2023 16:45:45 +0800
Subject: [PATCH] Upload

---
 config.json             | 23 +++++++++++++++++++++++
 pytorch_model.bin       |  3 +++
 special_tokens_map.json | 23 +++++++++++++++++++++++
 tokenizer.model         |  3 +++
 tokenizer_config.json   | 34 ++++++++++++++++++++++++++++++++++
 5 files changed, 86 insertions(+)
 create mode 100644 config.json
 create mode 100644 pytorch_model.bin
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer.model
 create mode 100644 tokenizer_config.json

diff --git a/config.json b/config.json
new file mode 100644
index 0000000..b54f5dc
--- /dev/null
+++ b/config.json
@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "MiniMA-3B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 49216
+}
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..cf0c08c
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e64e665a7d3fb59f34fe7c9bfe6e0e5ad69413b803b7ac6db21c60acdfde234
+size 6040967525
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..d85ba6c
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..14cb1e6
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae87c0db2b21b0fa3fdc5e19d1f9cea94efb703cc7c6281d8718a6714b3cc2be
+size 748869
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..64f06a6
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": true
+}