Add weights

README.md

@@ -1,3 +1,14 @@
 ---
 license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4/blob/main/LICENSE
+language:
+  - en
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
+tags:
+  - chat
 ---
+
+4-bit [GPTQ](https://arxiv.org/abs/2210.17323) quantized version of [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) for use with the [Private LLM app](https://privatellm.app/).

config.json

@@ -0,0 +1,5 @@
+{
+  "quantization_config": {
+        "bits": 4
+    }
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a22ca81a6baff987b593192cb829d3f0675fb1a2127a3fe3fc163381d4214a3
+size 116686848

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dcbc19f8b0440b8835c52159c047f7a2e095c40127a205a966713d33150e2c
+size 27787264

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9124793624fb02daff1f23997ed30a30f78721d7fb1d46e2bc7263e6f33891f6
+size 24137728

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44318af3196ebff4c1c8620bafc26788ff79cb312b3e3452d6fbe9295073afbf
+size 24137728

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d83cc03cf1365b246a393668d40523f04c311f714a60f8cc1e34bf7ed21a3c
+size 24137728

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b33518df8cf47e031b668e02c07d3d275ebe270d236288b3402ec7dfbd9d1d
+size 24137728

params_shard_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8510264a8e0db1c55fc281499c8685905cc7fd9958c5c3dc2a67400f688221
+size 24137728

params_shard_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653e0cd8b314478636c150a9a69a6b08753e01936c30dd0a212813fd109186c0
+size 24137728

params_shard_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df9fd7cb9f7e7f83855cfb3e53761f9d27ff93200535cf728d33c7479e58d5d
+size 24137728

params_shard_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b7dceaee1eecf1633748145ea55c6d84c933efb4c05137cad4fe9422d2c1c4
+size 24137728

params_shard_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b134d59f9d88d809fc3b4561884760d764b63f28e3ef7700426ed8b68e3494
+size 24137728

params_shard_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c083ef1451c11a62974b5fdc377c7af5c13ea795eeee3d48f9008a5edf3d5e
+size 24137728

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646fca097d9e3d92d61d92a278629ccb3ca29911d6b9140c56e8e29170d5b5a4
+size 31234048

params_shard_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593537051fe5fb2cb9e5e76a9cf4c09733bf347f52eaedcb102b8c50aab7798d
+size 24137728

params_shard_21.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c658c78645a026d1a132ef9d5bf79177cb1f0d7a29c023c604188a2d088b4935
+size 24137728

params_shard_22.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2702bb1ee6751bfa2ce874bd85386fd88289536aa50f337278291778899d2fc4
+size 24137728

params_shard_23.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40d6415898d497cbd150d820274b000f8b60eecc0a9e9063c412f0e32985416
+size 24137728

params_shard_24.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7723f198057b27e686d604ca62aa974af7fd43b4902f29c001a63768ccc4f933
+size 24137728

params_shard_25.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e75cc52b885bcb45596d35b2370e1f3b103acee7a93c172760cc3497e7fa464
+size 24137728

params_shard_26.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a173810558fb512ce5107d2a417afff7e5ffda7faaee9c3c859ddf7f85db69
+size 24137728

params_shard_27.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b879074544f56846535cd0201c111961a3b28b744f0967aa0f92738632bf1a0
+size 24137728

params_shard_28.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8947fd5c6f3c3f3af6ac9c27963e1316b67f05fc515049346f2a7ac208839b
+size 17041408

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67bf51fd745447b91b8128cf3ca0061a11e659444ebb7f727fb3976fb5eec983
+size 24137728

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5097043e6ba7e70396264b5d36ddf43dca5b16265b950a89a1bc5faa292143d2
+size 24137728

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9869b521bf4670548fa00a1f609b635870a20bff88caedf4f79f2ae10c2d1458
+size 24137728

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06afacf995b354b27a989c1df06c21c30213c1167756fe152b50cb1ae4ada728
+size 24137728

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfdf1c2bd831044e83e4d6ce7ce3b7704fc707a21b117c2b61bb44fd5817fcfc
+size 24137728

params_shard_8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a4cd68f010f126651e74fea87ebccb6c9ea2b333d03f9c34897a75bf25b4e9
+size 24137728

params_shard_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d133e8fa1759be8d21fe865e2d025712e6d47087aaa916e5ea476fac50a3fa8
+size 24137728

private-llm-config.json

@@ -0,0 +1,50 @@
+{
+  "model_type": "qwen2",
+  "quantization": "GPTQ-Int4",
+  "model_config": {
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "intermediate_size": 8960,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "vocab_size": 151936,
+    "tie_word_embeddings": true,
+    "context_window_size": 8192,
+    "prefill_chunk_size": 128,
+    "tensor_parallel_shards": 1,
+    "head_dim": 128,
+    "dtype": "float32",
+    "max_batch_size": 80
+  },
+  "vocab_size": 151936,
+  "context_window_size": 8192,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 128,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 128,
+  "max_gen_len": 512,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "conv_template": "qwen2",
+  "pad_token_id": 151643,
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "tokenizer_files": [
+    "tokenizer.json",
+    "vocab.json",
+    "merges.txt",
+    "tokenizer_config.json"
+  ],
+  "version": "0.1.0"
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}