model full update

README.md

@@ -1,8 +1,3 @@
----
-library_name: transformers
-tags: []
----
-
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->

adapter_config.json

@@ -1,35 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": {
-    "base_model_class": "Qwen2ForCausalLM",
-    "parent_library": "transformers.models.qwen2.modeling_qwen2"
-  },
-  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
-  "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "v_proj"
-  ],
-  "task_type": null,
-  "use_dora": false,
-  "use_rslora": false
-}

added_tokens.json

@@ -1,6 +1,7 @@
 {
   "</tool_call>": 151658,
   "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

config.json

@@ -1,15 +1,46 @@
 {
-    "model_type": "qwen2",
-    "hidden_size": 4096,
-    "num_attention_heads": 32,
-    "num_hidden_layers": 40,
-    "vocab_size": 65024,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "pad_token_id": 0,
-    "use_cache": true,
-    "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
-    "architectures": [
-        "Qwen2ForCausalLM"
-    ]
-}
+  "_name_or_path": "unsloth/Qwen2.5-7B-Instruct-bnb-4bit",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151665,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -1,6 +1,15 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 20,
+  "top_p": 0.1,
   "transformers_version": "4.47.0"
 }

adapter_model.safetensors → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d580a047c1eb6ec7d8c32af85f4deca1cf4e64eaa0c9bedeb25c4337b065007
-size 10107280
+oid sha256:5f7e3bd33a6bb71b162985e0f590127f2ade8788698e502bb60d647b52891668
+size 4457259166

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
+size 1089994880

special_tokens_map.json

@@ -15,14 +15,14 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|PAD_TOKEN|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e667a7d18d94098aefa2473386a7a3e456dff729cdf04a1f060f32b0d8b8fe7
-size 11422176
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -177,6 +177,14 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -195,21 +203,15 @@
     "<|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",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a Python expert.\nReturn ONLY the function implementation with no additional text or explanations.\n\nHere are some examples:\n\nex.1\n\n\nquery:\nwrite a function def analyze_nested_json(data, key_paths, value_types) to:\nAnalyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n\nThe function should output with:\ndict: A dictionary mapping types to lists of extracted values.\n\nYou should start with:\n\\`\\`\\`\nimport json\nimport defaultdict\nimport chain\nimport pandas as pd\nimport numpy as np\ndef analyze_nested_json(data, key_paths, value_types) \\`\\`\\`\n\n\nresponse:\nimport json\nfrom collections import defaultdict\nfrom itertools import chain\nimport pandas as pd\nimport numpy as np\n\ndef analyze_nested_json(data, key_paths, value_types):\n    \"\"\"\n    Analyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n    \n    Parameters:\n        - data (dict): A nested JSON data structure.\n        - key_paths (List[str]): Paths to keys in the JSON structure.\n        - value_types (List[type]): Types to categorize the extracted values.\n        \n    Requirements:\n        - json\n        - collections\n        - itertools\n        - pandas\n        - numpy\n    \n    Example:\n    >>> data = {\n    ...     \"root\": {\n    ...         \"child1\": {\"name\": \"Alice\", \"age\": 30, \"is_student\": False},\n    ...         \"child2\": {\"name\": \"Bob\", \"age\": 25, \"is_student\": True},\n    ...         \"child3\": {\"name\": \"Charlie\", \"age\": 35, \"is_student\": False},\n    ...         \"child4\": {\"name\": \"David\", \"age\": 22, \"is_student\": True}\n    ...     }\n    ... }\n    >>> key_paths = [\"root.child1.age\", \"root.child2.is_student\", \"root.child3.name\"]\n    >>> value_types = [int, bool, str]\n    >>> result = analyze_nested_json(data, key_paths, value_types)\n    >>> print(result)\n    {\n        \\'int\\': [30, 25, 35, 22],\n        \\'bool\\': [False, True, False, True],\n        \\'str\\': [\\'Alice\\', \\'Bob\\', \\'Charlie\\', \\'David\\']\n    }\n    \n    Returns:\n        dict: A dictionary mapping types to lists of extracted values.\n    \"\"\"\n    \n    def get_value_from_path(data, path):\n        keys = path.split(\\'.\\')\n        value = data\n        for key in keys:\n            value = value.get(key)\n            if value is None:\n                return None\n        return value\n    \n    categorized_values = defaultdict(list)\n    \n    for key_path, value_type in zip(key_paths, value_types):\n        value = get_value_from_path(data, key_path)\n        if isinstance(value, value_type):\n            categorized_values[str(value_type)].append(value)\n    \n    return dict(categorized_values)\n\n' }}\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 a Python expert.\nReturn ONLY the function implementation with no additional text or explanations.\n\nHere are some examples:\n\nex.1\n\n\nquery:\nwrite a function def analyze_nested_json(data, key_paths, value_types) to:\nAnalyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n\nThe function should output with:\ndict: A dictionary mapping types to lists of extracted values.\n\nYou should start with:\n\\`\\`\\`\nimport json\nimport defaultdict\nimport chain\nimport pandas as pd\nimport numpy as np\ndef analyze_nested_json(data, key_paths, value_types) \\`\\`\\`\n\n\nresponse:\nimport json\nfrom collections import defaultdict\nfrom itertools import chain\nimport pandas as pd\nimport numpy as np\n\ndef analyze_nested_json(data, key_paths, value_types):\n    \"\"\"\n    Analyzes a nested JSON structure to extract values at specified keys and categorize them based on their types.\n    \n    Parameters:\n        - data (dict): A nested JSON data structure.\n        - key_paths (List[str]): Paths to keys in the JSON structure.\n        - value_types (List[type]): Types to categorize the extracted values.\n        \n    Requirements:\n        - json\n        - collections\n        - itertools\n        - pandas\n        - numpy\n    \n    Example:\n    >>> data = {\n    ...     \"root\": {\n    ...         \"child1\": {\"name\": \"Alice\", \"age\": 30, \"is_student\": False},\n    ...         \"child2\": {\"name\": \"Bob\", \"age\": 25, \"is_student\": True},\n    ...         \"child3\": {\"name\": \"Charlie\", \"age\": 35, \"is_student\": False},\n    ...         \"child4\": {\"name\": \"David\", \"age\": 22, \"is_student\": True}\n    ...     }\n    ... }\n    >>> key_paths = [\"root.child1.age\", \"root.child2.is_student\", \"root.child3.name\"]\n    >>> value_types = [int, bool, str]\n    >>> result = analyze_nested_json(data, key_paths, value_types)\n    >>> print(result)\n    {\n        \\'int\\': [30, 25, 35, 22],\n        \\'bool\\': [False, True, False, True],\n        \\'str\\': [\\'Alice\\', \\'Bob\\', \\'Charlie\\', \\'David\\']\n    }\n    \n    Returns:\n        dict: A dictionary mapping types to lists of extracted values.\n    \"\"\"\n    \n    def get_value_from_path(data, path):\n        keys = path.split(\\'.\\')\n        value = data\n        for key in keys:\n            value = value.get(key)\n            if value is None:\n                return None\n        return value\n    \n    categorized_values = defaultdict(list)\n    \n    for key_path, value_type in zip(key_paths, value_types):\n        value = get_value_from_path(data, key_path)\n        if isinstance(value, value_type):\n            categorized_values[str(value_type)].append(value)\n    \n    return dict(categorized_values)\n\n<|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": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "max_length": 1024,
-  "model_max_length": 32768,
-  "pad_to_multiple_of": null,
-  "pad_token": "<|endoftext|>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
   "split_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": null
 }