upload model

README.md

@@ -1,3 +1,34 @@
 ---
 license: gpl-3.0
 ---
+# **NanoTranslator-M**
+
+## Introduction
+
+这是 NanoTranslator 的 Medium 型号，目前仅支持**英译中**。仓库中同时提供了 ONNX 版本的模型。
+
+
+
+| Size | Params. |  V.  |  H.  |  I.  |  L.  | Att. H. | KV H. | Tie Emb. |
+| :--: | :-----: | :--: | :--: | :--: | :--: | :-----: | :---: | :------: |
+|  XL  |  50 M   | 8000 | 320  | 1792 |  24  |   16    |   4   |   True   |
+|  L   |  22 M   | 8000 | 256  | 1408 |  16  |   16    |   4   |   True   |
+|  M   |  9 M  | 4000 | 168 | 896 |  16  |   12    |   4   |   True   |
+|  S   | 2 M  | 2000 |  96  | 512  |  12  |   12    |   4   |   True   |
+
+- **V.** - vocab size
+- **H.** - hidden size
+- **I.** - intermediate size
+- **L.** - num layers
+- **Att. H.** - num attention heads
+- **KV H.** - num kv heads
+- **Tie Emb.** - tie word embeddings
+
+
+
+## How to use
+
+### Normal
+
+
+### ONNX

README_zh-CN.md

@@ -0,0 +1,34 @@
+---
+license: gpl-3.0
+---
+# **NanoTranslator-M**
+
+## Introduction
+
+这是 NanoTranslator 的 Medium 型号，目前仅支持**英译中**。仓库中同时提供了 ONNX 版本的模型。
+
+
+
+| Size | Params. |  V.  |  H.  |  I.  |  L.  | Att. H. | KV H. | Tie Emb. |
+| :--: | :-----: | :--: | :--: | :--: | :--: | :-----: | :---: | :------: |
+|  XL  |  50 M   | 8000 | 320  | 1792 |  24  |   16    |   4   |   True   |
+|  L   |  22 M   | 8000 | 256  | 1408 |  16  |   16    |   4   |   True   |
+|  M   |  9 M  | 4000 | 168 | 896 |  16  |   12    |   4   |   True   |
+|  S   | 2 M  | 2000 |  96  | 512  |  12  |   12    |   4   |   True   |
+
+- **V.** - vocab size
+- **H.** - hidden size
+- **I.** - intermediate size
+- **L.** - num layers
+- **Att. H.** - num attention heads
+- **KV H.** - num kv heads
+- **Tie Emb.** - tie word embeddings
+
+
+
+## How to use
+
+### Normal
+
+
+### ONNX

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Mxode/NanoTranslator-M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 168,
+  "initializer_range": 0.02,
+  "intermediate_size": 896,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 4000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03231736c84087bc4a26cce8818e53ec641adccaef3a300b765d40030dc8756d
+size 36444280

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|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|>",
+  "errors": "replace",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}