upload model

README.md

@@ -65,6 +65,7 @@ def translate(text: str, model, **kwargs):
         temperature = kwargs.pop("temperature", 0.55),
         top_p = kwargs.pop("top_p", 0.8),
         top_k = kwargs.pop("top_k", 40),
+        eos_token_id = kwargs.pop("eos_token_id", tokenizer.eos_token_id),
         **kwargs
     )
 
@@ -124,6 +125,6 @@ pipe = pipeline("text-generation", model=model_path, accelerator="ort")
 
 text = "I love to watch my favorite TV series."
 
-response = pipe(text, max_new_tokens=64, do_sample=False)
+response = pipe(text, max_new_tokens=64, do_sample=False, eos_token_id=2)
 response
 ```

README_zh-CN.md

@@ -53,6 +53,7 @@ def translate(text: str, model, **kwargs):
         temperature = kwargs.pop("temperature", 0.55),
         top_p = kwargs.pop("top_p", 0.8),
         top_k = kwargs.pop("top_k", 40),
+        eos_token_id = kwargs.pop("eos_token_id", tokenizer.eos_token_id),
         **kwargs
     )
 
@@ -98,7 +99,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 text = "I love to watch my favorite TV series."
 
-response = translate(text, ort_model, max_new_tokens=64, do_sample=False)
+response = translate(text, ort_model, max_new_tokens=64, do_sample=False, eos_token_id=tokenizer.eos_token_id)
 print(response)
 ```
 
@@ -112,6 +113,6 @@ pipe = pipeline("text-generation", model=model_path, accelerator="ort")
 
 text = "I love to watch my favorite TV series."
 
-response = pipe(text, max_new_tokens=64, do_sample=False)
+response = pipe(text, max_new_tokens=64, do_sample=False, eos_token_id=2)
 response
 ```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/mnt/bn/gmma/zxt/model/nt-m22",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 432,
+  "initializer_range": 0.02,
+  "intermediate_size": 2304,
+  "max_position_embeddings": 1024,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 4000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4329e7f733b180e2d0ca995fd2ca386fa0555a0bd555883f54f80761e484711
+size 90567272

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": 1024,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}