初始化项目，由ModelHub XC社区提供模型

Model: jeffcookio/granite-3.3-8b-instruct-gptqmodel-4b-64g
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,4 @@
+---
+base_model:
+- ibm-granite/granite-3.3-8b-instruct
+---

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<|end_of_cite|>": 49156,
+  "<|end_of_plugin|>": 49158,
+  "<|end_of_role|>": 49153,
+  "<|start_of_cite|>": 49155,
+  "<|start_of_plugin|>": 49157,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

chat_template.jinja

@@ -0,0 +1,78 @@
+{# Alias tools -> available_tools #}
+{%- if tools and not available_tools -%}
+    {%- set available_tools = tools -%}
+{%- endif -%}
+{%- set user_system_message -%}
+    {%- for msg in messages if msg['role'] == 'system' -%}
+        {%- if msg['content'] is string -%}
+            {{- msg['content'] + "\n" }}
+        {%- else -%}
+            {%- for contents in msg['content'] if contents['type'] == 'text' -%}
+                {{- contents['text'] + "\n" }}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endset -%}
+{%- set loop_messages = messages|rejectattr("role", "==", "system") -%}
+{%- set system_message = " Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ". You are Granite, developed by IBM." %}
+{%- if available_tools and documents %}
+    {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request. 
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+{%- elif available_tools %}
+    {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+{%- elif documents %}
+    {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+{%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+{%- else %}
+    {%- set system_message = system_message + " You are a helpful AI assistant." %}
+{%- endif %}
+{%- if 'citations' in controls and documents %}
+    {%- set system_message = system_message + ' 
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+{%- endif %}
+{%- if 'hallucinations' in controls and documents %}
+    {%- set system_message = system_message + ' 
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+{%- endif %}
+{{- '<|start_of_role|>system<|end_of_role|>' + system_message + "\n\n---\n\n" + user_system_message + '<|end_of_text|>
+' }}
+{%- if available_tools %}
+    {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+    {{- available_tools | tojson(indent=4) }}
+    {{- '<|end_of_text|>
+    ' }}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+        {{- document['text'] }}
+        {{- '<|end_of_text|>
+' }}
+    {%- endfor %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message['content'] is not string %}
+       {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' }}
+       {%- for msg in message['content'] %}
+           {%- if msg['type'] == 'text' %}
+               {{- msg['text'] }}
+           {%- endif %}
+       {%- endfor %}
+       {{- '<|end_of_text|>
+' }}
+    {%- else %}
+         {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+    {%- endif %}
+    {%- if loop.last and add_generation_prompt %}
+        {{- '<|start_of_role|>assistant' }}
+            {%- if controls %}
+                {{- ' ' + controls | tojson()}}
+            {%- endif %}
+        {{- '<|end_of_role|>' }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "group_size": 64,
+    "lm_head": false,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantized_by": "jeffcookio",
+      "quantizer": [
+        "gptqmodel:3.0.0-dev"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "v2": false,
+      "v2_alpha": 0.25
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "vocab_size": 49159
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.0.dev0"
+}

granite-3.3b-8b-instruct.coaelsced_system.jinja

@@ -0,0 +1,78 @@
+{# Alias tools -> available_tools #}
+{%- if tools and not available_tools -%}
+    {%- set available_tools = tools -%}
+{%- endif -%}
+{%- set user_system_message -%}
+    {%- for msg in messages if msg['role'] == 'system' -%}
+        {%- if msg['content'] is string -%}
+            {{- msg['content'] + "\n" }}
+        {%- else -%}
+            {%- for contents in msg['content'] if contents['type'] == 'text' -%}
+                {{- contents['text'] + "\n" }}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endset -%}
+{%- set loop_messages = messages|rejectattr("role", "==", "system") -%}
+{%- set system_message = " Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ". You are Granite, developed by IBM." %}
+{%- if available_tools and documents %}
+    {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request. 
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+{%- elif available_tools %}
+    {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+{%- elif documents %}
+    {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+{%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+{%- else %}
+    {%- set system_message = system_message + " You are a helpful AI assistant." %}
+{%- endif %}
+{%- if 'citations' in controls and documents %}
+    {%- set system_message = system_message + ' 
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+{%- endif %}
+{%- if 'hallucinations' in controls and documents %}
+    {%- set system_message = system_message + ' 
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+{%- endif %}
+{{- '<|start_of_role|>system<|end_of_role|>' + system_message + "\n\n---\n\n" + user_system_message + '<|end_of_text|>
+' }}
+{%- if available_tools %}
+    {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+    {{- available_tools | tojson(indent=4) }}
+    {{- '<|end_of_text|>
+    ' }}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+        {{- document['text'] }}
+        {{- '<|end_of_text|>
+' }}
+    {%- endfor %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message['content'] is not string %}
+       {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' }}
+       {%- for msg in message['content'] %}
+           {%- if msg['type'] == 'text' %}
+               {{- msg['text'] }}
+           {%- endif %}
+       {%- endfor %}
+       {{- '<|end_of_text|>
+' }}
+    {%- else %}
+         {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+    {%- endif %}
+    {%- if loop.last and add_generation_prompt %}
+        {{- '<|start_of_role|>assistant' }}
+            {%- if controls %}
+                {{- ' ' + controls | tojson()}}
+            {%- endif %}
+        {{- '<|end_of_role|>' }}
+    {%- endif %}
+{%- endfor %}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca356c3961970d56da885b2e42f7828d7dd4260a71b30406d1d020b8bb7fa0a6
+size 3975078600

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393025f45fc143a7e82070e4950de5af7f4a6a30d83f073ef9ae426c54bcb583
+size 730295464

quant_log.csv

@@ -0,0 +1,281 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.0000586761,0.01000,1.322
+0,self_attn.v_proj,0.0000354517,0.01000,0.423
+0,self_attn.q_proj,0.0001688128,0.01000,0.814
+0,self_attn.o_proj,0.0000504424,0.01000,0.412
+0,mlp.up_proj,0.0002153337,0.01000,0.477
+0,mlp.gate_proj,0.0001274616,0.01000,0.477
+0,mlp.down_proj,0.0000257240,0.01000,1.993
+1,self_attn.k_proj,0.0001001337,0.01000,0.431
+1,self_attn.v_proj,0.0000342787,0.01000,0.584
+1,self_attn.q_proj,0.0002745207,0.01000,0.443
+1,self_attn.o_proj,0.0000241509,0.01000,0.438
+1,mlp.up_proj,0.0003969561,0.01000,0.475
+1,mlp.gate_proj,0.0002391965,0.01000,0.483
+1,mlp.down_proj,0.0000294897,0.01000,1.630
+2,self_attn.k_proj,0.0001192039,0.01000,0.404
+2,self_attn.v_proj,0.0000332262,0.01000,0.411
+2,self_attn.q_proj,0.0002993230,0.01000,0.420
+2,self_attn.o_proj,0.0000098605,0.01000,0.427
+2,mlp.up_proj,0.0003834351,0.01000,0.476
+2,mlp.gate_proj,0.0003096603,0.01000,0.617
+2,mlp.down_proj,0.0000365176,0.01000,2.022
+3,self_attn.k_proj,0.0002040798,0.01000,0.423
+3,self_attn.v_proj,0.0000696390,0.01000,0.427
+3,self_attn.q_proj,0.0006119413,0.01000,0.432
+3,self_attn.o_proj,0.0000065294,0.01000,0.508
+3,mlp.up_proj,0.0003998308,0.01000,0.550
+3,mlp.gate_proj,0.0003683545,0.01000,0.531
+3,mlp.down_proj,0.0000227664,0.01000,1.659
+4,self_attn.k_proj,0.0001992193,0.01000,0.414
+4,self_attn.v_proj,0.0000724991,0.01000,0.399
+4,self_attn.q_proj,0.0005812223,0.01000,0.418
+4,self_attn.o_proj,0.0000047541,0.01000,0.415
+4,mlp.up_proj,0.0003851807,0.01000,0.488
+4,mlp.gate_proj,0.0003571671,0.01000,0.482
+4,mlp.down_proj,0.0000273872,0.01000,1.597
+5,self_attn.k_proj,0.0002788666,0.01000,0.396
+5,self_attn.v_proj,0.0000720661,0.01000,0.403
+5,self_attn.q_proj,0.0007805153,0.01000,0.411
+5,self_attn.o_proj,0.0000036737,0.01000,0.410
+5,mlp.up_proj,0.0003783789,0.01000,0.472
+5,mlp.gate_proj,0.0003321028,0.01000,0.480
+5,mlp.down_proj,0.0010589203,0.01000,1.561
+6,self_attn.k_proj,0.0002729923,0.01000,0.425
+6,self_attn.v_proj,0.0001261053,0.01000,0.403
+6,self_attn.q_proj,0.0008447057,0.01000,0.405
+6,self_attn.o_proj,0.0000053821,0.01000,0.409
+6,mlp.up_proj,0.0004143942,0.01000,0.469
+6,mlp.gate_proj,0.0003667180,0.01000,0.467
+6,mlp.down_proj,0.0000214279,0.01000,1.551
+7,self_attn.k_proj,0.0001874382,0.01000,0.405
+7,self_attn.v_proj,0.0000727971,0.01000,0.416
+7,self_attn.q_proj,0.0005578802,0.01000,0.413
+7,self_attn.o_proj,0.0000066064,0.01000,0.410
+7,mlp.up_proj,0.0003853983,0.01000,0.475
+7,mlp.gate_proj,0.0003386188,0.01000,0.473
+7,mlp.down_proj,0.0000226514,0.01000,1.591
+8,self_attn.k_proj,0.0002412666,0.01000,0.454
+8,self_attn.v_proj,0.0000851461,0.01000,0.396
+8,self_attn.q_proj,0.0007171566,0.01000,0.405
+8,self_attn.o_proj,0.0000049167,0.01000,0.404
+8,mlp.up_proj,0.0003648815,0.01000,0.469
+8,mlp.gate_proj,0.0003146806,0.01000,0.469
+8,mlp.down_proj,0.0000242255,0.01000,1.566
+9,self_attn.k_proj,0.0002791988,0.01000,0.402
+9,self_attn.v_proj,0.0000772140,0.01000,0.397
+9,self_attn.q_proj,0.0008410137,0.01000,0.408
+9,self_attn.o_proj,0.0000074889,0.01000,0.410
+9,mlp.up_proj,0.0003793764,0.01000,0.480
+9,mlp.gate_proj,0.0003070541,0.01000,0.466
+9,mlp.down_proj,0.0000285720,0.01000,1.561
+10,self_attn.k_proj,0.0002847525,0.01000,0.401
+10,self_attn.v_proj,0.0000690638,0.01000,0.401
+10,self_attn.q_proj,0.0007431567,0.01000,0.408
+10,self_attn.o_proj,0.0000112762,0.01000,0.401
+10,mlp.up_proj,0.0003249209,0.01000,0.473
+10,mlp.gate_proj,0.0002650708,0.01000,0.468
+10,mlp.down_proj,0.0000318138,0.01000,1.563
+11,self_attn.k_proj,0.0003096352,0.01000,0.401
+11,self_attn.v_proj,0.0000897225,0.01000,0.400
+11,self_attn.q_proj,0.0008893770,0.01000,0.407
+11,self_attn.o_proj,0.0000122147,0.01000,0.406
+11,mlp.up_proj,0.0003072199,0.01000,0.479
+11,mlp.gate_proj,0.0002517828,0.01000,0.483
+11,mlp.down_proj,0.0000332955,0.01000,1.573
+12,self_attn.k_proj,0.0003948360,0.01000,0.405
+12,self_attn.v_proj,0.0000998961,0.01000,0.402
+12,self_attn.q_proj,0.0012023712,0.01000,0.416
+12,self_attn.o_proj,0.0000106507,0.01000,0.414
+12,mlp.up_proj,0.0003385118,0.01000,0.472
+12,mlp.gate_proj,0.0002744211,0.01000,0.484
+12,mlp.down_proj,0.0000393885,0.01000,1.570
+13,self_attn.k_proj,0.0003714790,0.01000,0.401
+13,self_attn.v_proj,0.0001324728,0.01000,0.396
+13,self_attn.q_proj,0.0010769964,0.01000,0.406
+13,self_attn.o_proj,0.0000178290,0.01000,0.406
+13,mlp.up_proj,0.0003482320,0.01000,0.472
+13,mlp.gate_proj,0.0002787499,0.01000,0.470
+13,mlp.down_proj,0.0000429903,0.01000,1.559
+14,self_attn.k_proj,0.0003436909,0.01000,0.404
+14,self_attn.v_proj,0.0001705214,0.01000,0.404
+14,self_attn.q_proj,0.0010559997,0.01000,0.409
+14,self_attn.o_proj,0.0000169769,0.01000,0.433
+14,mlp.up_proj,0.0003698721,0.01000,0.479
+14,mlp.gate_proj,0.0002898470,0.01000,0.481
+14,mlp.down_proj,0.0000458820,0.01000,1.589
+15,self_attn.k_proj,0.0003220908,0.01000,0.407
+15,self_attn.v_proj,0.0001672515,0.01000,0.403
+15,self_attn.q_proj,0.0010098481,0.01000,0.410
+15,self_attn.o_proj,0.0000213154,0.01000,0.405
+15,mlp.up_proj,0.0003779694,0.01000,0.489
+15,mlp.gate_proj,0.0002958367,0.01000,0.477
+15,mlp.down_proj,0.0000516704,0.01000,1.591
+16,self_attn.k_proj,0.0003507759,0.01000,0.402
+16,self_attn.v_proj,0.0001544250,0.01000,0.396
+16,self_attn.q_proj,0.0010080066,0.01000,0.404
+16,self_attn.o_proj,0.0000288016,0.01000,0.401
+16,mlp.up_proj,0.0003919088,0.01000,0.468
+16,mlp.gate_proj,0.0003031051,0.01000,0.468
+16,mlp.down_proj,0.0000538878,0.01000,1.553
+17,self_attn.k_proj,0.0003736942,0.01000,0.400
+17,self_attn.v_proj,0.0001494565,0.01000,0.395
+17,self_attn.q_proj,0.0010871407,0.01000,0.413
+17,self_attn.o_proj,0.0000141816,0.01000,0.422
+17,mlp.up_proj,0.0004607816,0.01000,0.472
+17,mlp.gate_proj,0.0003417494,0.01000,0.476
+17,mlp.down_proj,0.0000554428,0.01000,1.569
+18,self_attn.k_proj,0.0003214898,0.01000,0.407
+18,self_attn.v_proj,0.0001460328,0.01000,0.403
+18,self_attn.q_proj,0.0009515478,0.01000,0.406
+18,self_attn.o_proj,0.0000206779,0.01000,0.407
+18,mlp.up_proj,0.0004685978,0.01000,0.472
+18,mlp.gate_proj,0.0003603305,0.01000,0.471
+18,mlp.down_proj,0.0000611692,0.01000,1.573
+19,self_attn.k_proj,0.0003957018,0.01000,0.398
+19,self_attn.v_proj,0.0001980347,0.01000,0.397
+19,self_attn.q_proj,0.0012038962,0.01000,0.403
+19,self_attn.o_proj,0.0000182705,0.01000,0.405
+19,mlp.up_proj,0.0004899677,0.01000,0.469
+19,mlp.gate_proj,0.0003855893,0.01000,0.470
+19,mlp.down_proj,0.0000754451,0.01000,1.578
+20,self_attn.k_proj,0.0000000000,0.01000,0.412
+20,self_attn.v_proj,0.0000001169,0.01000,0.398
+20,self_attn.q_proj,0.0000000000,0.01000,0.406
+20,self_attn.o_proj,0.0000000019,0.01000,0.405
+20,mlp.up_proj,0.0005356293,0.01000,0.506
+20,mlp.gate_proj,0.0004464875,0.01000,0.497
+20,mlp.down_proj,0.0000753395,0.01000,1.704
+21,self_attn.k_proj,0.0004827192,0.01000,0.455
+21,self_attn.v_proj,0.0002100711,0.01000,0.423
+21,self_attn.q_proj,0.0013876994,0.01000,0.446
+21,self_attn.o_proj,0.0000157326,0.01000,0.429
+21,mlp.up_proj,0.0005929679,0.01000,0.534
+21,mlp.gate_proj,0.0005037194,0.01000,0.550
+21,mlp.down_proj,0.0000908208,0.01000,1.741
+22,self_attn.k_proj,0.0004898814,0.01000,0.461
+22,self_attn.v_proj,0.0002796991,0.01000,0.430
+22,self_attn.q_proj,0.0015202498,0.01000,0.463
+22,self_attn.o_proj,0.0000083112,0.01000,0.420
+22,mlp.up_proj,0.0006740890,0.01000,0.525
+22,mlp.gate_proj,0.0005844082,0.01000,0.522
+22,mlp.down_proj,0.0001015973,0.01000,1.680
+23,self_attn.k_proj,0.0000000000,0.01000,0.419
+23,self_attn.v_proj,0.0000000540,0.01000,0.454
+23,self_attn.q_proj,0.0000000000,0.01000,0.431
+23,self_attn.o_proj,0.0000000004,0.01000,0.448
+23,mlp.up_proj,0.0007605743,0.01000,0.530
+23,mlp.gate_proj,0.0006684575,0.01000,0.485
+23,mlp.down_proj,0.0001126684,0.01000,1.681
+24,self_attn.k_proj,0.0000000000,0.01000,0.443
+24,self_attn.v_proj,0.0000000667,0.01000,0.424
+24,self_attn.q_proj,0.0000000000,0.01000,0.442
+24,self_attn.o_proj,0.0000000005,0.01000,0.454
+24,mlp.up_proj,0.0008429098,0.01000,0.508
+24,mlp.gate_proj,0.0007483406,0.01000,0.533
+24,mlp.down_proj,0.0001261322,0.01000,1.699
+25,self_attn.k_proj,0.0006377540,0.01000,0.455
+25,self_attn.v_proj,0.0004328548,0.01000,0.426
+25,self_attn.q_proj,0.0020318676,0.01000,0.461
+25,self_attn.o_proj,0.0000157571,0.01000,0.429
+25,mlp.up_proj,0.0009439098,0.01000,0.526
+25,mlp.gate_proj,0.0008411989,0.01000,0.562
+25,mlp.down_proj,0.0001479721,0.01000,1.709
+26,self_attn.k_proj,0.0000000000,0.01000,0.449
+26,self_attn.v_proj,0.0000001092,0.01000,0.453
+26,self_attn.q_proj,0.0000000000,0.01000,0.464
+26,self_attn.o_proj,0.0000000007,0.01000,0.428
+26,mlp.up_proj,0.0010536772,0.01000,0.558
+26,mlp.gate_proj,0.0009431117,0.01000,0.549
+26,mlp.down_proj,0.0001719375,0.01000,1.696
+27,self_attn.k_proj,0.0000000000,0.01000,0.421
+27,self_attn.v_proj,0.0000001668,0.01000,0.445
+27,self_attn.q_proj,0.0000000000,0.01000,0.424
+27,self_attn.o_proj,0.0000000011,0.01000,0.447
+27,mlp.up_proj,0.0011833173,0.01000,0.506
+27,mlp.gate_proj,0.0010602921,0.01000,0.482
+27,mlp.down_proj,0.0001971719,0.01000,1.692
+28,self_attn.k_proj,0.0006555448,0.01000,0.455
+28,self_attn.v_proj,0.0005032099,0.01000,0.427
+28,self_attn.q_proj,0.0021870123,0.01000,0.441
+28,self_attn.o_proj,0.0000279065,0.01000,0.437
+28,mlp.up_proj,0.0013163162,0.01000,0.497
+28,mlp.gate_proj,0.0011671635,0.01000,0.510
+28,mlp.down_proj,0.0002391058,0.01000,1.691
+29,self_attn.k_proj,0.0000000000,0.01000,0.438
+29,self_attn.v_proj,0.0000007706,0.01000,0.452
+29,self_attn.q_proj,0.0000000000,0.01000,0.475
+29,self_attn.o_proj,0.0000000089,0.01000,0.445
+29,mlp.up_proj,0.0014455931,0.01000,0.548
+29,mlp.gate_proj,0.0012611508,0.01000,0.525
+29,mlp.down_proj,0.0002838329,0.01000,1.793
+30,self_attn.k_proj,0.0006660341,0.01000,0.440
+30,self_attn.v_proj,0.0006107283,0.01000,0.455
+30,self_attn.q_proj,0.0023818917,0.01000,0.443
+30,self_attn.o_proj,0.0000448454,0.01000,0.435
+30,mlp.up_proj,0.0015934884,0.01000,0.517
+30,mlp.gate_proj,0.0013594907,0.01000,0.494
+30,mlp.down_proj,0.0003501898,0.01000,1.681
+31,self_attn.k_proj,0.0007014952,0.01000,0.448
+31,self_attn.v_proj,0.0006060585,0.01000,0.434
+31,self_attn.q_proj,0.0023846514,0.01000,0.451
+31,self_attn.o_proj,0.0000715734,0.01000,0.464
+31,mlp.up_proj,0.0018080392,0.01000,0.497
+31,mlp.gate_proj,0.0014998679,0.01000,0.518
+31,mlp.down_proj,0.0004398297,0.01000,1.681
+32,self_attn.k_proj,0.0007654972,0.01000,0.516
+32,self_attn.v_proj,0.0008954310,0.01000,0.581
+32,self_attn.q_proj,0.0028394967,0.01000,0.455
+32,self_attn.o_proj,0.0000516377,0.01000,0.435
+32,mlp.up_proj,0.0019804822,0.01000,0.535
+32,mlp.gate_proj,0.0016116200,0.01000,0.539
+32,mlp.down_proj,0.0006111872,0.01000,1.698
+33,self_attn.k_proj,0.0006394647,0.01000,0.466
+33,self_attn.v_proj,0.0006978745,0.01000,0.449
+33,self_attn.q_proj,0.0023009892,0.01000,0.460
+33,self_attn.o_proj,0.0000961008,0.01000,0.434
+33,mlp.up_proj,0.0021798046,0.01000,0.520
+33,mlp.gate_proj,0.0017339357,0.01000,0.526
+33,mlp.down_proj,0.0008359131,0.01000,1.690
+34,self_attn.k_proj,0.0006541725,0.01000,0.440
+34,self_attn.v_proj,0.0011296207,0.01000,0.479
+34,self_attn.q_proj,0.0025815739,0.01000,0.459
+34,self_attn.o_proj,0.0001475956,0.01000,0.440
+34,mlp.up_proj,0.0025971491,0.01000,0.569
+34,mlp.gate_proj,0.0019881812,0.01000,0.502
+34,mlp.down_proj,0.0010410425,0.01000,1.719
+35,self_attn.k_proj,0.0005942605,0.01000,0.422
+35,self_attn.v_proj,0.0012088416,0.01000,0.440
+35,self_attn.q_proj,0.0025064127,0.01000,0.422
+35,self_attn.o_proj,0.0001772174,0.01000,0.449
+35,mlp.up_proj,0.0030033083,0.01000,0.513
+35,mlp.gate_proj,0.0022048278,0.01000,0.495
+35,mlp.down_proj,0.0015544999,0.01000,1.684
+36,self_attn.k_proj,0.0005515935,0.01000,0.448
+36,self_attn.v_proj,0.0019261715,0.01000,0.425
+36,self_attn.q_proj,0.0024816982,0.01000,0.459
+36,self_attn.o_proj,0.0001544181,0.01000,0.439
+36,mlp.up_proj,0.0039325399,0.01000,0.496
+36,mlp.gate_proj,0.0028782809,0.01000,0.522
+36,mlp.down_proj,0.0022360407,0.01000,1.667
+37,self_attn.k_proj,0.0005540850,0.01000,0.428
+37,self_attn.v_proj,0.0023931593,0.01000,0.449
+37,self_attn.q_proj,0.0026355596,0.01000,0.450
+37,self_attn.o_proj,0.0002773240,0.01000,0.435
+37,mlp.up_proj,0.0040397442,0.01000,0.527
+37,mlp.gate_proj,0.0029825685,0.01000,0.515
+37,mlp.down_proj,0.0030968198,0.01000,1.671
+38,self_attn.k_proj,0.0004877125,0.01000,0.436
+38,self_attn.v_proj,0.0039252046,0.01000,0.444
+38,self_attn.q_proj,0.0026660137,0.01000,0.424
+38,self_attn.o_proj,0.0005240002,0.01000,0.449
+38,mlp.up_proj,0.0042532832,0.01000,0.500
+38,mlp.gate_proj,0.0033421522,0.01000,0.502
+38,mlp.down_proj,0.0052362741,0.01000,1.683
+39,self_attn.k_proj,0.0005696468,0.01000,0.438
+39,self_attn.v_proj,0.0035458919,0.01000,0.418
+39,self_attn.q_proj,0.0035293297,0.01000,0.447
+39,self_attn.o_proj,0.0016652486,0.01000,0.427
+39,mlp.up_proj,0.0042222063,0.01000,0.524
+39,mlp.gate_proj,0.0035428723,0.01000,0.524
+39,mlp.down_proj,0.0119190907,0.01000,1.665

quantize_config.json

@@ -0,0 +1,24 @@
+{
+  "bits": 4,
+  "group_size": 64,
+  "desc_act": true,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantized_by": "jeffcookio",
+    "quantizer": [
+      "gptqmodel:3.0.0-dev"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.0025,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "v2": false,
+    "v2_alpha": 0.25
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>",
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}