upload auto_gptq

Signed-off-by: n1ck-guo <[email protected]>

config.json

@@ -19,11 +19,11 @@
   "quantization_config": {
     "amp": true,
     "autoround_version": "0.4.2",
-    "backend": "auto_round:gptq:exllamav2",
     "batch_size": 8,
     "bits": 2,
+    "damp_percent": 0.01,
     "data_type": "int",
-    "dataset": "NeelNanda/pile-10k",
+    "desc_act": false,
     "enable_minmax_tuning": true,
     "enable_norm_bias_tuning": false,
     "enable_quanted_input": true,
@@ -34,11 +34,12 @@
     "lr": 0.0005,
     "minmax_lr": 0.0005,
     "nsamples": 1024,
-    "quant_method": "intel/auto-round",
+    "quant_method": "gptq",
     "scale_dtype": "torch.float16",
     "seqlen": 2048,
     "sym": true,
-    "to_quant_block_names": null
+    "to_quant_block_names": null,
+    "true_sequential": false
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:704b52b6074a16c10bab88925c6c8df9f8a774ec87cd21e68e7cd2cf1b2c8769
+oid sha256:2397d8397bb52d5256453f9305babe26337048de676ca715830c7093ff61836f
 size 4997831816

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9498984817f3ffccc4885b53129e73ad32496dd1ab7bf56148131818ad3aab
+oid sha256:e0a5e68a8d9cbd5798f6b952ff0c4ee879629f08bd73fbafdd0f06bdeed02b2e
 size 4943608520

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e864a5c47671dee16ddefad23ebdce2cd6dad6dd16733b06d8849497c97543
+oid sha256:bafbd7cfc6c96122263cca61694c8fa5b0aa5490b5efda94b70b63b975c4dc4c
 size 4943727032

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7613e3932ba7c44e825db22f8d6dc2dd81bcd23ff5275f9efd27287d17448968
+oid sha256:df77ba4efd8d8d3a47ebd32c36f19b3e4f91e2fa454e0afb73a38cadd9d39a57
 size 4943727024

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51b7d191285acf680909cb6a521cab4e19c092b12c1318cde5bb3a05fdd6e38
+oid sha256:26dd7eb3beed75238cf0090c5287be83889375527f20fca1d24ee43f9170fbc0
 size 2713862656

quantize_config.json

@@ -0,0 +1,25 @@
+{
+  "bits": 2,
+  "group_size": 64,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 2048,
+  "batch_size": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 0.0005,
+  "minmax_lr": 0.0005,
+  "gradient_accumulate_steps": 1,
+  "iters": 2000,
+  "amp": true,
+  "nsamples": 1024,
+  "low_gpu_mem_usage": true,
+  "to_quant_block_names": null,
+  "enable_norm_bias_tuning": false,
+  "autoround_version": "0.4.2",
+  "quant_method": "gptq",
+  "desc_act": false,
+  "true_sequential": false,
+  "damp_percent": 0.01
+}

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
       "content": "<|endoftext|>",
@@ -177,12 +179,29 @@
       "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": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}
+  "unk_token": null
+}