Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Models/70/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Models/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Models/50/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

Models/50/config.json

@@ -0,0 +1,82 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "format": "gptq",
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": true,
+      "auto_forward_data_parallel": true,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.05,
+      "failsafe": {
+        "smooth": null,
+        "strategy": "rtn",
+        "threshold": "0.5%"
+      },
+      "gc_mode": "interval",
+      "gptaq": null,
+      "hessian": {
+        "chunk_bytes": null,
+        "chunk_size": null,
+        "staging_dtype": "float32"
+      },
+      "mock_quantization": false,
+      "mse": 0.0,
+      "offload_to_disk": true,
+      "offload_to_disk_path": "./gptqmodel_offload/pthyuejg-tgujncci/",
+      "pack_impl": "cpu",
+      "quantizer": [
+        "gptqmodel:5.8.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "vram_strategy": "exclusive",
+      "wait_for_submodule_finalizers": false
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

Models/50/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.2.0"
+}

Models/50/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d756ce8fb90e545e5b47ef1566bc3cbdca3a6ded02e0e31ba7fed2b04dec3d6
+size 2255767880

Models/50/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000003655,0.05000,6.135
+0,self_attn.q_proj,0.0000139163,0.05000,6.251
+0,self_attn.k_proj,0.0000070522,0.05000,6.287
+0,self_attn.o_proj,0.0000000161,0.05000,1.438
+0,mlp.up_proj,0.0000059081,0.05000,3.042
+0,mlp.gate_proj,0.0000067841,0.05000,3.079
+0,mlp.down_proj,0.0000000707,0.05000,3.574
+1,self_attn.q_proj,0.0000158107,0.05000,6.250
+1,self_attn.k_proj,0.0000093271,0.05000,6.342
+1,self_attn.v_proj,0.0000009569,0.05000,6.403
+1,self_attn.o_proj,0.0000000717,0.05000,1.268
+1,mlp.gate_proj,0.0000085050,0.05000,2.909
+1,mlp.up_proj,0.0000074407,0.05000,2.938
+1,mlp.down_proj,0.0000020780,0.05000,3.624
+2,self_attn.v_proj,0.0000035664,0.05000,6.128
+2,self_attn.k_proj,0.0000384627,0.05000,6.183
+2,self_attn.q_proj,0.0000636528,0.05000,6.217
+2,self_attn.o_proj,0.0000000483,0.05000,1.279
+2,mlp.gate_proj,0.0000133714,0.05000,2.891
+2,mlp.up_proj,0.0000112456,0.05000,2.918
+2,mlp.down_proj,0.0000001836,0.05000,3.592
+3,self_attn.k_proj,0.0000209325,0.05000,6.104
+3,self_attn.q_proj,0.0000374590,0.05000,6.210
+3,self_attn.v_proj,0.0000032397,0.05000,6.243
+3,self_attn.o_proj,0.0000000519,0.05000,1.242
+3,mlp.gate_proj,0.0000199032,0.05000,2.985
+3,mlp.up_proj,0.0000147765,0.05000,3.037
+3,mlp.down_proj,0.0000002623,0.05000,3.622
+4,self_attn.k_proj,0.0000209495,0.05000,6.247
+4,self_attn.v_proj,0.0000035178,0.05000,6.307
+4,self_attn.q_proj,0.0000402571,0.05000,6.356
+4,self_attn.o_proj,0.0000001683,0.05000,1.296
+4,mlp.gate_proj,0.0000267916,0.05000,3.001
+4,mlp.up_proj,0.0000176318,0.05000,3.032
+4,mlp.down_proj,0.0000004458,0.05000,3.538
+5,self_attn.q_proj,0.0000566906,0.05000,6.143
+5,self_attn.k_proj,0.0000350725,0.05000,6.192
+5,self_attn.v_proj,0.0000035867,0.05000,6.259
+5,self_attn.o_proj,0.0000002498,0.05000,1.254
+5,mlp.up_proj,0.0000200849,0.05000,2.861
+5,mlp.gate_proj,0.0000287105,0.05000,2.907
+5,mlp.down_proj,0.0000006270,0.05000,3.494
+6,self_attn.q_proj,0.0000456653,0.05000,6.164
+6,self_attn.k_proj,0.0000243565,0.05000,6.213
+6,self_attn.v_proj,0.0000032720,0.05000,6.258
+6,self_attn.o_proj,0.0000002966,0.05000,1.271
+6,mlp.gate_proj,0.0000316156,0.05000,2.851
+6,mlp.up_proj,0.0000221315,0.05000,2.875
+6,mlp.down_proj,0.0000007019,0.05000,3.596
+7,self_attn.k_proj,0.0000232553,0.05000,6.241
+7,self_attn.q_proj,0.0000390834,0.05000,6.349
+7,self_attn.v_proj,0.0000030140,0.05000,6.364
+7,self_attn.o_proj,0.0000005020,0.05000,1.230
+7,mlp.gate_proj,0.0000300552,0.05000,2.820
+7,mlp.up_proj,0.0000227827,0.05000,2.857
+7,mlp.down_proj,0.0000007818,0.05000,3.548
+8,self_attn.k_proj,0.0000296915,0.05000,6.160
+8,self_attn.q_proj,0.0000489327,0.05000,6.220
+8,self_attn.v_proj,0.0000035765,0.05000,6.250
+8,self_attn.o_proj,0.0000005180,0.05000,1.287
+8,mlp.gate_proj,0.0000325682,0.05000,3.116
+8,mlp.up_proj,0.0000241525,0.05000,3.147
+8,mlp.down_proj,0.0000007777,0.05000,3.697
+9,self_attn.k_proj,0.0000279815,0.05000,6.365
+9,self_attn.q_proj,0.0000470294,0.05000,6.415
+9,self_attn.v_proj,0.0000045795,0.05000,6.444
+9,self_attn.o_proj,0.0000005254,0.05000,1.274
+9,mlp.gate_proj,0.0000318904,0.05000,3.054
+9,mlp.up_proj,0.0000243400,0.05000,3.097
+9,mlp.down_proj,0.0000007917,0.05000,3.662
+10,self_attn.v_proj,0.0000035862,0.05000,6.390
+10,self_attn.k_proj,0.0000299603,0.05000,6.439
+10,self_attn.q_proj,0.0000476768,0.05000,6.472
+10,self_attn.o_proj,0.0000006423,0.05000,1.260
+10,mlp.gate_proj,0.0000323488,0.05000,3.004
+10,mlp.up_proj,0.0000264711,0.05000,3.029
+10,mlp.down_proj,0.0000009133,0.05000,3.569
+11,self_attn.v_proj,0.0000042222,0.05000,6.385
+11,self_attn.q_proj,0.0000389616,0.05000,6.432
+11,self_attn.k_proj,0.0000221590,0.05000,6.478
+11,self_attn.o_proj,0.0000007108,0.05000,1.303
+11,mlp.gate_proj,0.0000346920,0.05000,3.147
+11,mlp.up_proj,0.0000293260,0.05000,3.189
+11,mlp.down_proj,0.0000010680,0.05000,3.578
+12,self_attn.v_proj,0.0000049074,0.05000,6.397
+12,self_attn.q_proj,0.0000599314,0.05000,6.425
+12,self_attn.k_proj,0.0000360839,0.05000,6.448
+12,self_attn.o_proj,0.0000008251,0.05000,1.306
+12,mlp.up_proj,0.0000314120,0.05000,3.121
+12,mlp.gate_proj,0.0000372577,0.05000,3.155
+12,mlp.down_proj,0.0000012126,0.05000,3.640
+13,self_attn.k_proj,0.0000389678,0.05000,6.532
+13,self_attn.q_proj,0.0000606843,0.05000,6.581
+13,self_attn.v_proj,0.0000056146,0.05000,6.603
+13,self_attn.o_proj,0.0000009978,0.05000,1.232
+13,mlp.gate_proj,0.0000445419,0.05000,3.054
+13,mlp.up_proj,0.0000351055,0.05000,3.085
+13,mlp.down_proj,0.0000015760,0.05000,3.608
+14,self_attn.q_proj,0.0000686343,0.05000,6.346
+14,self_attn.k_proj,0.0000314004,0.05000,6.429
+14,self_attn.v_proj,0.0000066387,0.05000,6.455
+14,self_attn.o_proj,0.0000012561,0.05000,1.325
+14,mlp.up_proj,0.0000375102,0.05000,2.993
+14,mlp.gate_proj,0.0000478461,0.05000,3.019
+14,mlp.down_proj,0.0000019180,0.05000,3.639
+15,self_attn.v_proj,0.0000065177,0.05000,6.382
+15,self_attn.q_proj,0.0000684232,0.05000,6.478
+15,self_attn.k_proj,0.0000357806,0.05000,6.490
+15,self_attn.o_proj,0.0000009062,0.05000,1.253
+15,mlp.up_proj,0.0000374816,0.05000,3.019
+15,mlp.gate_proj,0.0000510690,0.05000,3.046
+15,mlp.down_proj,0.0000019322,0.05000,3.550
+16,self_attn.q_proj,0.0000697884,0.05000,6.246
+16,self_attn.v_proj,0.0000073443,0.05000,6.299
+16,self_attn.k_proj,0.0000398958,0.05000,6.347
+16,self_attn.o_proj,0.0000005650,0.05000,1.274
+16,mlp.up_proj,0.0000372290,0.05000,3.057
+16,mlp.gate_proj,0.0000518827,0.05000,3.110
+16,mlp.down_proj,0.0000018123,0.05000,3.574
+17,self_attn.v_proj,0.0000071509,0.05000,6.345
+17,self_attn.k_proj,0.0000360828,0.05000,6.390
+17,self_attn.q_proj,0.0000662234,0.05000,6.422
+17,self_attn.o_proj,0.0000005764,0.05000,1.277
+17,mlp.gate_proj,0.0000540872,0.05000,3.071
+17,mlp.up_proj,0.0000382789,0.05000,3.121
+17,mlp.down_proj,0.0000019723,0.05000,3.628
+18,self_attn.q_proj,0.0000768960,0.05000,6.232
+18,self_attn.v_proj,0.0000090087,0.05000,6.312
+18,self_attn.k_proj,0.0000426919,0.05000,6.348
+18,self_attn.o_proj,0.0000005129,0.05000,1.306
+18,mlp.up_proj,0.0000403784,0.05000,3.084
+18,mlp.gate_proj,0.0000557208,0.05000,3.102
+18,mlp.down_proj,0.0000020153,0.05000,3.576
+19,self_attn.k_proj,0.0000391191,0.05000,6.414
+19,self_attn.q_proj,0.0000672697,0.05000,6.462
+19,self_attn.v_proj,0.0000086852,0.05000,6.490
+19,self_attn.o_proj,0.0000007129,0.05000,1.348
+19,mlp.up_proj,0.0000428687,0.05000,3.091
+19,mlp.gate_proj,0.0000584434,0.05000,3.129
+19,mlp.down_proj,0.0000024692,0.05000,3.558
+20,self_attn.v_proj,0.0000102000,0.05000,6.572
+20,self_attn.k_proj,0.0000419316,0.05000,6.646
+20,self_attn.q_proj,0.0000693657,0.05000,6.679
+20,self_attn.o_proj,0.0000005730,0.05000,1.440
+20,mlp.up_proj,0.0000435856,0.05000,3.067
+20,mlp.gate_proj,0.0000564082,0.05000,3.126
+20,mlp.down_proj,0.0000023884,0.05000,3.670
+21,self_attn.k_proj,0.0000410597,0.05000,6.395
+21,self_attn.v_proj,0.0000134331,0.05000,6.524
+21,self_attn.q_proj,0.0000694150,0.05000,6.547
+21,self_attn.o_proj,0.0000006532,0.05000,1.324
+21,mlp.gate_proj,0.0000595703,0.05000,3.093
+21,mlp.up_proj,0.0000455969,0.05000,3.126
+21,mlp.down_proj,0.0000025119,0.05000,3.593
+22,self_attn.k_proj,0.0000379314,0.05000,6.376
+22,self_attn.q_proj,0.0000656641,0.05000,6.415
+22,self_attn.v_proj,0.0000129559,0.05000,6.437
+22,self_attn.o_proj,0.0000006026,0.05000,1.297
+22,mlp.up_proj,0.0000487634,0.05000,3.087
+22,mlp.gate_proj,0.0000640544,0.05000,3.115
+22,mlp.down_proj,0.0000028967,0.05000,3.652
+23,self_attn.q_proj,0.0000680379,0.05000,6.571
+23,self_attn.v_proj,0.0000125475,0.05000,6.652
+23,self_attn.k_proj,0.0000421066,0.05000,6.674
+23,self_attn.o_proj,0.0000008360,0.05000,1.300
+23,mlp.gate_proj,0.0000771958,0.05000,3.051
+23,mlp.up_proj,0.0000553964,0.05000,3.084
+23,mlp.down_proj,0.0000037663,0.05000,3.648
+24,self_attn.q_proj,0.0000738199,0.05000,6.379
+24,self_attn.v_proj,0.0000189734,0.05000,6.423
+24,self_attn.k_proj,0.0000465050,0.05000,6.477
+24,self_attn.o_proj,0.0000014266,0.05000,1.281
+24,mlp.up_proj,0.0000596369,0.05000,3.043
+24,mlp.gate_proj,0.0000848039,0.05000,3.081
+24,mlp.down_proj,0.0000043019,0.05000,3.599
+25,self_attn.k_proj,0.0000343078,0.05000,6.722
+25,self_attn.q_proj,0.0000664509,0.05000,6.772
+25,self_attn.v_proj,0.0000153221,0.05000,6.806
+25,self_attn.o_proj,0.0000016806,0.05000,1.262
+25,mlp.gate_proj,0.0000898007,0.05000,3.004
+25,mlp.up_proj,0.0000626860,0.05000,3.051
+25,mlp.down_proj,0.0000053409,0.05000,3.695
+26,self_attn.v_proj,0.0000210691,0.05000,6.411
+26,self_attn.q_proj,0.0000636958,0.05000,6.472
+26,self_attn.k_proj,0.0000403479,0.05000,6.524
+26,self_attn.o_proj,0.0000014542,0.05000,1.290
+26,mlp.up_proj,0.0000650641,0.05000,3.043
+26,mlp.gate_proj,0.0000945761,0.05000,3.087
+26,mlp.down_proj,0.0000081644,0.05000,3.669
+27,self_attn.v_proj,0.0000141159,0.05000,6.830
+27,self_attn.k_proj,0.0000273797,0.05000,6.913
+27,self_attn.q_proj,0.0000486121,0.05000,6.940
+27,self_attn.o_proj,0.0000070236,0.05000,1.345
+27,mlp.gate_proj,0.0000950958,0.05000,3.230
+27,mlp.up_proj,0.0000753671,0.05000,3.255
+27,mlp.down_proj,0.0000416984,0.05000,3.798

Models/50/quantize_config.json

@@ -0,0 +1,42 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": false,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:5.8.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "gptaq": null,
+    "act_group_aware": true,
+    "failsafe": {
+      "strategy": "rtn",
+      "threshold": "0.5%",
+      "smooth": null
+    },
+    "offload_to_disk": true,
+    "offload_to_disk_path": "./gptqmodel_offload/pthyuejg-tgujncci/",
+    "pack_impl": "cpu",
+    "mock_quantization": false,
+    "gc_mode": "interval",
+    "wait_for_submodule_finalizers": false,
+    "auto_forward_data_parallel": true,
+    "hessian": {
+      "chunk_size": null,
+      "chunk_bytes": null,
+      "staging_dtype": "float32"
+    },
+    "vram_strategy": "exclusive"
+  },
+  "sym": true,
+  "format": "gptq"
+}

Models/50/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70650b4236027dc8db4abca6b918783a8ed2ee38cd69142f6dbbeb5945f876f
+size 17210195

Models/50/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}