upload

README.md

@@ -22,13 +22,14 @@ All models are collected in the [NanoTranslator Collection](https://huggingface.
 
 |  | P. | Arch. | Act. |  V.  |  H.  |  I.  |  L.  | A.H. | K.H. | Tie |
 | :--: | :-----: | :--: | :--: | :--: | :-----: | :---: | :------: | :--: | :--: | :--: |
-|  [XXL](https://huggingface.co/Mxode/NanoTranslator-XXL)  |  100  |  LLaMA  |  SwiGLU  | 16000 | 768  | 4096 |  8   |  24  |  8   | True |
-|  [XL](https://huggingface.co/Mxode/NanoTranslator-XL)  |  78  | LLaMA | GeGLU  | 16000 | 768  | 4096 |  6   |  24  |  8   | True |
-| [L](https://huggingface.co/Mxode/NanoTranslator-L) |  49  | LLaMA | GeGLU  | 16000 | 512  | 2816 |  8   |  16  |  8   | True |
-| [M2](https://huggingface.co/Mxode/NanoTranslator-M2) | 22 | Qwen2 | GeGLU | 4000  | 432  | 2304 |  6   |  24  |  8   | True |
-|  [M](https://huggingface.co/Mxode/NanoTranslator-M)   |  22  |  LLaMA  |  SwiGLU  | 8000  | 256  | 1408 |  16  |  16  |  4   | True |
-|  [S](https://huggingface.co/Mxode/NanoTranslator-S)   | 9 | LLaMA | SwiGLU | 4000  | 168  | 896  |  16  |  12  |  4   | True |
-| [XS](https://huggingface.co/Mxode/NanoTranslator-XS) | 2 | LLaMA | SwiGLU | 2000 | 96 | 512 | 12 | 12 | 4 | True |
+| [XXL2](https://huggingface.co/Mxode/NanoTranslator-XXL2) | 102 | LLaMA | SwiGLU | 16K | 1120 | 3072 | 6 | 16 | 8 | True |
+|  [XXL](https://huggingface.co/Mxode/NanoTranslator-XXL)  |  100  |  LLaMA  |  SwiGLU  | 16K | 768  | 4096 |  8   |  24  |  8   | True |
+|  [XL](https://huggingface.co/Mxode/NanoTranslator-XL)  |  78  | LLaMA | GeGLU  | 16K | 768  | 4096 |  6   |  24  |  8   | True |
+| [L](https://huggingface.co/Mxode/NanoTranslator-L) |  49  | LLaMA | GeGLU  | 16K | 512  | 2816 |  8   |  16  |  8   | True |
+| [M2](https://huggingface.co/Mxode/NanoTranslator-M2) | 22 | Qwen2 | GeGLU | 4K | 432  | 2304 |  6   |  24  |  8   | True |
+|  [M](https://huggingface.co/Mxode/NanoTranslator-M)   |  22  |  LLaMA  |  SwiGLU  | 8K | 256  | 1408 |  16  |  16  |  4   | True |
+|  [S](https://huggingface.co/Mxode/NanoTranslator-S)   | 9 | LLaMA | SwiGLU | 4K | 168  | 896  |  16  |  12  |  4   | True |
+| [XS](https://huggingface.co/Mxode/NanoTranslator-XS) | 2 | LLaMA | SwiGLU | 2K | 96 | 512 | 12 | 12 | 4 | True |
 
 - **P.** - Parameters (in million)
 - **V.** - vocab size
@@ -81,7 +82,7 @@ def translate(text: str, model, **kwargs):
     response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
     return response
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = translate(text, model, max_new_tokens=64, do_sample=False)
 print(response)
@@ -110,7 +111,7 @@ model_path = "your/folder/to/onnx_model"
 ort_model = ORTModelForCausalLM.from_pretrained(model_path)
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = translate(text, ort_model, max_new_tokens=64, do_sample=False)
 print(response)
@@ -124,7 +125,7 @@ from optimum.pipelines import pipeline
 model_path = "your/folder/to/onnx_model"
 pipe = pipeline("text-generation", model=model_path, accelerator="ort")
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = pipe(text, max_new_tokens=64, do_sample=False)
 response

README_zh-CN.md

@@ -10,13 +10,14 @@
 
 |  | P. | Arch. | Act. |  V.  |  H.  |  I.  |  L.  | A.H. | K.H. | Tie |
 | :--: | :-----: | :--: | :--: | :--: | :-----: | :---: | :------: | :--: | :--: | :--: |
-|  [XXL](https://huggingface.co/Mxode/NanoTranslator-XXL)  |  100  |  LLaMA  |  SwiGLU  | 16000 | 768  | 4096 |  8   |  24  |  8   | True |
-|  [XL](https://huggingface.co/Mxode/NanoTranslator-XL)  |  78  | LLaMA | GeGLU  | 16000 | 768  | 4096 |  6   |  24  |  8   | True |
-| [L](https://huggingface.co/Mxode/NanoTranslator-L) |  49  | LLaMA | GeGLU  | 16000 | 512  | 2816 |  8   |  16  |  8   | True |
-| [M2](https://huggingface.co/Mxode/NanoTranslator-M2) | 22 | Qwen2 | GeGLU | 4000  | 432  | 2304 |  6   |  24  |  8   | True |
-|  [M](https://huggingface.co/Mxode/NanoTranslator-M)   |  22  |  LLaMA  |  SwiGLU  | 8000  | 256  | 1408 |  16  |  16  |  4   | True |
-|  [S](https://huggingface.co/Mxode/NanoTranslator-S)   | 9 | LLaMA | SwiGLU | 4000  | 168  | 896  |  16  |  12  |  4   | True |
-| [XS](https://huggingface.co/Mxode/NanoTranslator-XS) | 2 | LLaMA | SwiGLU | 2000 | 96 | 512 | 12 | 12 | 4 | True |
+| [XXL2](https://huggingface.co/Mxode/NanoTranslator-XXL2) | 102 | LLaMA | SwiGLU | 16K | 1120 | 3072 | 6 | 16 | 8 | True |
+|  [XXL](https://huggingface.co/Mxode/NanoTranslator-XXL)  |  100  |  LLaMA  |  SwiGLU  | 16K | 768  | 4096 |  8   |  24  |  8   | True |
+|  [XL](https://huggingface.co/Mxode/NanoTranslator-XL)  |  78  | LLaMA | GeGLU  | 16K | 768  | 4096 |  6   |  24  |  8   | True |
+| [L](https://huggingface.co/Mxode/NanoTranslator-L) |  49  | LLaMA | GeGLU  | 16K | 512  | 2816 |  8   |  16  |  8   | True |
+| [M2](https://huggingface.co/Mxode/NanoTranslator-M2) | 22 | Qwen2 | GeGLU | 4K | 432  | 2304 |  6   |  24  |  8   | True |
+|  [M](https://huggingface.co/Mxode/NanoTranslator-M)   |  22  |  LLaMA  |  SwiGLU  | 8K | 256  | 1408 |  16  |  16  |  4   | True |
+|  [S](https://huggingface.co/Mxode/NanoTranslator-S)   | 9 | LLaMA | SwiGLU | 4K | 168  | 896  |  16  |  12  |  4   | True |
+| [XS](https://huggingface.co/Mxode/NanoTranslator-XS) | 2 | LLaMA | SwiGLU | 2K | 96 | 512 | 12 | 12 | 4 | True |
 
 - **P.** - Parameters (in million)
 - **V.** - vocab size
@@ -69,7 +70,7 @@ def translate(text: str, model, **kwargs):
     response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
     return response
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = translate(text, model, max_new_tokens=64, do_sample=False)
 print(response)
@@ -98,7 +99,7 @@ model_path = "your/folder/to/onnx_model"
 ort_model = ORTModelForCausalLM.from_pretrained(model_path)
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = translate(text, ort_model, max_new_tokens=64, do_sample=False)
 print(response)
@@ -112,7 +113,7 @@ from optimum.pipelines import pipeline
 model_path = "your/folder/to/onnx_model"
 pipe = pipeline("text-generation", model=model_path, accelerator="ort")
 
-text = "I love to watch my favorite TV series."
+text = "Each step of the cell cycle is monitored by internal."
 
 response = pipe(text, max_new_tokens=64, do_sample=False)
 response

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "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": 16000
+}

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:ece6d628a0f001cd501bfeee7182c632119519d5b5787b26bd3fc66d1ff0f4d3
+size 196388824

result.log

@@ -0,0 +1 @@
+{'train_runtime': 10636.9905, 'train_samples_per_second': 1509.392, 'train_steps_per_second': 2.948, 'train_loss': 1.2621650553170833, 'epoch': 1.0}

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"
+}