upload

README.md

@@ -82,7 +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)
@@ -111,7 +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)
@@ -125,7 +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

@@ -70,7 +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)
@@ -99,7 +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)
@@ -113,7 +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": "silu",
+  "hidden_size": 1120,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 6,
+  "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:e61e747d1807d95624209f67bdef6ae9941d53a311abc8fdfb48126a9903f2d7
+size 409787400

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"
+}