upload files

README.md

@@ -0,0 +1,122 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- zh
+- vi
+---
+[WN-zh-vi-sim-v0.3](https://huggingface.co/CjangCjengh/WN-zh-vi-sim-v0.3)的GPTQ Int4量化版本
+
+Bản quant GPTQ Int4 của [WN-zh-vi-sim-v0.3](https://huggingface.co/CjangCjengh/WN-zh-vi-sim-v0.3)
+
+模型用于对齐中文文本和越南语文本
+
+Mô hình dùng để align văn bản tiếng Trung và tiếng Việt
+
+```python
+import os
+import json
+import torch
+import torch.nn.functional as F
+from vllm import LLM
+from vllm.config import PoolerConfig
+
+model_path = 'CjangCjengh/WN-zh-vi-sim-v0.3-GPTQ-Int4'
+zh_text_path = 'zh.txt'
+vi_text_path = 'vi.txt'
+output_path = 'output.json'
+device = 'cuda'
+cpu_offload_gb = 0
+lm_head_path = f'{model_path}/yes_no_lm_head.pt'
+
+zh_idx = 0
+vi_idx = 0
+max_extra_lines = 5
+
+align_list = []
+if os.path.exists(output_path):
+    with open(output_path,'r',encoding='utf-8') as f:
+        align_list = json.load(f)
+        zh_idx = sum([i['zh'].count('\n')+1 for i in align_list if i['zh']])
+        vi_idx = sum([i['vi'].count('\n')+1 for i in align_list if i['vi']])
+
+lm_head = torch.load(lm_head_path)
+lm_head.to(device)
+
+llm = LLM(model=model_path, cpu_offload_gb=cpu_offload_gb, enforce_eager=True, task='embed', override_pooler_config=PoolerConfig(pooling_type='ALL'))
+
+zh_lines = open(zh_text_path,'r',encoding='utf-8').readlines()
+vi_lines = open(vi_text_path,'r',encoding='utf-8').readlines()
+zh_lines = [l.strip() for l in zh_lines]
+vi_lines = [l.strip() for l in vi_lines]
+
+
+def get_sim_score(src_text, tgt_text):
+    text = f'<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n下面的中文段落和越南语段落的内容是否完全对应，不存在缺漏？（回答Yes或No）\n\n中文：\n{src_text}\n\n越南语：{tgt_text}<|im_end|>\n<|im_start|>assistant\n'
+    outputs = llm.encode(text)
+    with torch.inference_mode():
+        hidden_states = outputs[0].outputs.data[-1].to(dtype=lm_head.dtype).to(device)
+        logits = torch.matmul(lm_head, hidden_states)
+        result = F.softmax(logits, dim=0).tolist()
+    return result[0]
+
+def generate_pairs():
+    visited = set()
+    size = 1
+    while True:
+        for x in range(size + 1):
+            for y in range(size + 1):
+                if (x, y) not in visited:
+                    visited.add((x, y))
+                    yield (x+1, y+1)
+        size += 1
+
+while zh_idx < len(zh_lines) and vi_idx < len(vi_lines):
+    for zh_i, vi_i in generate_pairs():
+        zh_text = ''.join(zh_lines[zh_idx:zh_idx+zh_i])
+        vi_text = ' '.join(vi_lines[vi_idx:vi_idx+vi_i])
+        score = get_sim_score(zh_text, vi_text)
+        if score > 0.5:
+            break
+        if zh_i == 1 and vi_i == 1:
+            continue
+        score = get_sim_score(zh_lines[zh_idx+zh_i-1], vi_lines[vi_idx+vi_i-1])
+        if score > 0.5:
+            zh_i -= 1
+            vi_i -= 1
+            break
+        if zh_i > max_extra_lines or vi_i > max_extra_lines:
+            end_flag = False
+            for zh_i, vi_i in generate_pairs():
+                if zh_i == 1 and vi_i == 1:
+                    continue
+                for zh_i_offset, vi_i_offset in generate_pairs():
+                    zh_start = zh_idx+zh_i-1
+                    vi_start = vi_idx+vi_i-1
+                    if zh_i+zh_i_offset > max_extra_lines and vi_i+vi_i_offset > max_extra_lines:
+                        break
+                    if zh_i+zh_i_offset > max_extra_lines or vi_i+vi_i_offset > max_extra_lines:
+                        continue
+                    score = get_sim_score(zh_lines[zh_start:zh_start+zh_i_offset], vi_lines[vi_start:vi_start+vi_i_offset])
+                    if score > 0.5:
+                        zh_i -= 1
+                        vi_i -= 1
+                        end_flag = True
+                        break
+                if end_flag:
+                    break
+                if zh_i > max_extra_lines or vi_i > max_extra_lines:
+                    raise Exception(f'Error! zh line No.{zh_idx+1} vi line No.{vi_idx+1}')
+
+    zh_text = '\n'.join(zh_lines[zh_idx:zh_idx+zh_i])
+    vi_text = '\n'.join(vi_lines[vi_idx:vi_idx+vi_i])
+    align_list.append({'zh':zh_text, 'vi':vi_text})
+
+    new_align = [list(range(zh_idx, zh_idx+zh_i)), list(range(vi_idx, vi_idx+vi_i))]
+    print(new_align)
+
+    with open(output_path,'w',encoding='utf-8') as f:
+        json.dump(align_list, f, ensure_ascii=False, indent=0)
+
+    zh_idx += zh_i
+    vi_idx += vi_i
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "qwen_align_zh_vi_4",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "desc_act": false,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "model_file_base_name": "model",
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301d610f41a440b600b69cef7ff9faadd0c2fd689d2b3fa691027f98b2a2a2f9
+size 9992417944

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "model",
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

yes_no_lm_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b03ed41c8107f64f369c97fca1e8bffb5942782f3de8e0b681209447ec1407a
+size 21695