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/25/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/hibgcqvy-hpwwspav/",
+      "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:a4d04048ad86686c28387ddc010af3d4fe33a653e6a99352597d465ee7a6b201
+size 2255767880

Models/50/quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000139680,0.05000,5.305
+0,self_attn.v_proj,0.0000003759,0.05000,5.383
+0,self_attn.k_proj,0.0000070846,0.05000,5.402
+0,self_attn.o_proj,0.0000000157,0.05000,1.004
+0,mlp.gate_proj,0.0000068226,0.05000,2.417
+0,mlp.up_proj,0.0000059404,0.05000,2.418
+0,mlp.down_proj,0.0000000725,0.05000,2.874
+1,self_attn.k_proj,0.0000095077,0.05000,5.638
+1,self_attn.v_proj,0.0000010649,0.05000,5.697
+1,self_attn.q_proj,0.0000162416,0.05000,5.717
+1,self_attn.o_proj,0.0000000565,0.05000,1.076
+1,mlp.gate_proj,0.0000087613,0.05000,2.989
+1,mlp.up_proj,0.0000076847,0.05000,3.024
+1,mlp.down_proj,0.0000018727,0.05000,3.125
+2,self_attn.q_proj,0.0000670399,0.05000,5.696
+2,self_attn.v_proj,0.0000039832,0.05000,5.768
+2,self_attn.k_proj,0.0000399288,0.05000,5.786
+2,self_attn.o_proj,0.0000000645,0.05000,1.049
+2,mlp.gate_proj,0.0000140579,0.05000,2.393
+2,mlp.up_proj,0.0000118356,0.05000,2.407
+2,mlp.down_proj,0.0000002062,0.05000,3.033
+3,self_attn.q_proj,0.0000403938,0.05000,4.883
+3,self_attn.v_proj,0.0000036359,0.05000,4.970
+3,self_attn.k_proj,0.0000225691,0.05000,4.991
+3,self_attn.o_proj,0.0000000964,0.05000,1.053
+3,mlp.up_proj,0.0000156097,0.05000,2.391
+3,mlp.gate_proj,0.0000210012,0.05000,2.412
+3,mlp.down_proj,0.0000003030,0.05000,3.005
+4,self_attn.q_proj,0.0000433604,0.05000,4.959
+4,self_attn.v_proj,0.0000040748,0.05000,5.001
+4,self_attn.k_proj,0.0000225520,0.05000,5.032
+4,self_attn.o_proj,0.0000001913,0.05000,1.017
+4,mlp.gate_proj,0.0000279136,0.05000,2.466
+4,mlp.up_proj,0.0000184692,0.05000,2.476
+4,mlp.down_proj,0.0000004594,0.05000,2.948
+5,self_attn.v_proj,0.0000041336,0.05000,4.881
+5,self_attn.k_proj,0.0000375154,0.05000,4.976
+5,self_attn.q_proj,0.0000616927,0.05000,4.982
+5,self_attn.o_proj,0.0000002548,0.05000,1.100
+5,mlp.up_proj,0.0000208768,0.05000,2.398
+5,mlp.gate_proj,0.0000297058,0.05000,2.419
+5,mlp.down_proj,0.0000006227,0.05000,2.969
+6,self_attn.k_proj,0.0000261515,0.05000,5.002
+6,self_attn.q_proj,0.0000491912,0.05000,5.060
+6,self_attn.v_proj,0.0000037164,0.05000,5.079
+6,self_attn.o_proj,0.0000003613,0.05000,1.029
+6,mlp.gate_proj,0.0000324102,0.05000,2.340
+6,mlp.up_proj,0.0000227860,0.05000,2.352
+6,mlp.down_proj,0.0000007253,0.05000,2.979
+7,self_attn.v_proj,0.0000032542,0.05000,4.959
+7,self_attn.q_proj,0.0000409642,0.05000,4.990
+7,self_attn.k_proj,0.0000242736,0.05000,5.024
+7,self_attn.o_proj,0.0000005799,0.05000,1.028
+7,mlp.up_proj,0.0000234077,0.05000,2.298
+7,mlp.gate_proj,0.0000306611,0.05000,2.321
+7,mlp.down_proj,0.0000008050,0.05000,2.968
+8,self_attn.v_proj,0.0000039600,0.05000,4.906
+8,self_attn.k_proj,0.0000308434,0.05000,4.953
+8,self_attn.q_proj,0.0000512178,0.05000,4.986
+8,self_attn.o_proj,0.0000006049,0.05000,1.060
+8,mlp.up_proj,0.0000246837,0.05000,2.312
+8,mlp.gate_proj,0.0000330912,0.05000,2.334
+8,mlp.down_proj,0.0000008281,0.05000,3.030
+9,self_attn.q_proj,0.0000488215,0.05000,4.915
+9,self_attn.k_proj,0.0000289286,0.05000,4.963
+9,self_attn.v_proj,0.0000049874,0.05000,4.988
+9,self_attn.o_proj,0.0000006253,0.05000,1.045
+9,mlp.up_proj,0.0000248506,0.05000,2.336
+9,mlp.gate_proj,0.0000323409,0.05000,2.342
+9,mlp.down_proj,0.0000008285,0.05000,3.060
+10,self_attn.v_proj,0.0000038885,0.05000,4.946
+10,self_attn.k_proj,0.0000307636,0.05000,4.983
+10,self_attn.q_proj,0.0000493704,0.05000,5.019
+10,self_attn.o_proj,0.0000007088,0.05000,1.017
+10,mlp.gate_proj,0.0000328339,0.05000,2.391
+10,mlp.up_proj,0.0000270201,0.05000,2.409
+10,mlp.down_proj,0.0000009400,0.05000,2.972
+11,self_attn.q_proj,0.0000401640,0.05000,4.869
+11,self_attn.v_proj,0.0000045547,0.05000,4.928
+11,self_attn.k_proj,0.0000226958,0.05000,4.982
+11,self_attn.o_proj,0.0000008010,0.05000,1.034
+11,mlp.gate_proj,0.0000345544,0.05000,2.392
+11,mlp.up_proj,0.0000293561,0.05000,2.400
+11,mlp.down_proj,0.0000010772,0.05000,3.015
+12,self_attn.k_proj,0.0000361648,0.05000,4.865
+12,self_attn.q_proj,0.0000607128,0.05000,4.983
+12,self_attn.v_proj,0.0000052258,0.05000,5.000
+12,self_attn.o_proj,0.0000010185,0.05000,1.020
+12,mlp.gate_proj,0.0000371353,0.05000,2.335
+12,mlp.up_proj,0.0000316075,0.05000,2.347
+12,mlp.down_proj,0.0000012233,0.05000,2.968
+13,self_attn.v_proj,0.0000059725,0.05000,4.970
+13,self_attn.q_proj,0.0000619890,0.05000,5.033
+13,self_attn.k_proj,0.0000395530,0.05000,5.056
+13,self_attn.o_proj,0.0000011513,0.05000,1.011
+13,mlp.gate_proj,0.0000444610,0.05000,2.320
+13,mlp.up_proj,0.0000352364,0.05000,2.340
+13,mlp.down_proj,0.0000016179,0.05000,3.016
+14,self_attn.v_proj,0.0000069888,0.05000,5.068
+14,self_attn.q_proj,0.0000696170,0.05000,5.098
+14,self_attn.k_proj,0.0000319154,0.05000,5.126
+14,self_attn.o_proj,0.0000014018,0.05000,1.034
+14,mlp.gate_proj,0.0000475400,0.05000,2.334
+14,mlp.up_proj,0.0000374746,0.05000,2.356
+14,mlp.down_proj,0.0000019131,0.05000,2.958
+15,self_attn.v_proj,0.0000069070,0.05000,4.931
+15,self_attn.q_proj,0.0000694283,0.05000,4.980
+15,self_attn.k_proj,0.0000361245,0.05000,5.006
+15,self_attn.o_proj,0.0000009409,0.05000,1.067
+15,mlp.up_proj,0.0000371522,0.05000,2.324
+15,mlp.gate_proj,0.0000503156,0.05000,2.343
+15,mlp.down_proj,0.0000019074,0.05000,3.047
+16,self_attn.k_proj,0.0000399651,0.05000,4.850
+16,self_attn.v_proj,0.0000076146,0.05000,4.928
+16,self_attn.q_proj,0.0000704941,0.05000,4.971
+16,self_attn.o_proj,0.0000006443,0.05000,1.035
+16,mlp.up_proj,0.0000365405,0.05000,2.331
+16,mlp.gate_proj,0.0000506454,0.05000,2.351
+16,mlp.down_proj,0.0000017757,0.05000,2.968
+17,self_attn.q_proj,0.0000665387,0.05000,4.831
+17,self_attn.v_proj,0.0000073697,0.05000,4.925
+17,self_attn.k_proj,0.0000360675,0.05000,4.959
+17,self_attn.o_proj,0.0000005999,0.05000,1.135
+17,mlp.gate_proj,0.0000523846,0.05000,2.339
+17,mlp.up_proj,0.0000372537,0.05000,2.362
+17,mlp.down_proj,0.0000019583,0.05000,2.957
+18,self_attn.v_proj,0.0000092865,0.05000,4.932
+18,self_attn.q_proj,0.0000767019,0.05000,4.971
+18,self_attn.k_proj,0.0000423681,0.05000,5.010
+18,self_attn.o_proj,0.0000005972,0.05000,1.011
+18,mlp.gate_proj,0.0000545215,0.05000,2.314
+18,mlp.up_proj,0.0000397141,0.05000,2.335
+18,mlp.down_proj,0.0000020258,0.05000,2.967
+19,self_attn.k_proj,0.0000392652,0.05000,4.891
+19,self_attn.q_proj,0.0000678425,0.05000,4.933
+19,self_attn.v_proj,0.0000090537,0.05000,4.961
+19,self_attn.o_proj,0.0000008387,0.05000,1.025
+19,mlp.gate_proj,0.0000570506,0.05000,2.278
+19,mlp.up_proj,0.0000419815,0.05000,2.298
+19,mlp.down_proj,0.0000025156,0.05000,2.970
+20,self_attn.k_proj,0.0000415792,0.05000,4.948
+20,self_attn.q_proj,0.0000694669,0.05000,4.995
+20,self_attn.v_proj,0.0000106951,0.05000,5.019
+20,self_attn.o_proj,0.0000006934,0.05000,1.078
+20,mlp.up_proj,0.0000426496,0.05000,2.360
+20,mlp.gate_proj,0.0000549296,0.05000,2.369
+20,mlp.down_proj,0.0000024157,0.05000,2.975
+21,self_attn.q_proj,0.0000692564,0.05000,4.916
+21,self_attn.k_proj,0.0000408783,0.05000,4.951
+21,self_attn.v_proj,0.0000139237,0.05000,4.966
+21,self_attn.o_proj,0.0000008302,0.05000,1.034
+21,mlp.gate_proj,0.0000580645,0.05000,2.358
+21,mlp.up_proj,0.0000446525,0.05000,2.373
+21,mlp.down_proj,0.0000025897,0.05000,2.969
+22,self_attn.q_proj,0.0000659685,0.05000,4.862
+22,self_attn.k_proj,0.0000378584,0.05000,4.965
+22,self_attn.v_proj,0.0000134829,0.05000,4.988
+22,self_attn.o_proj,0.0000007891,0.05000,1.037
+22,mlp.up_proj,0.0000472200,0.05000,2.298
+22,mlp.gate_proj,0.0000617282,0.05000,2.326
+22,mlp.down_proj,0.0000030136,0.05000,3.058
+23,self_attn.k_proj,0.0000415418,0.05000,4.939
+23,self_attn.q_proj,0.0000675351,0.05000,4.964
+23,self_attn.v_proj,0.0000132672,0.05000,5.006
+23,self_attn.o_proj,0.0000010529,0.05000,1.018
+23,mlp.up_proj,0.0000528725,0.05000,2.424
+23,mlp.gate_proj,0.0000733665,0.05000,2.454
+23,mlp.down_proj,0.0000039680,0.05000,2.920
+24,self_attn.k_proj,0.0000455178,0.05000,4.938
+24,self_attn.v_proj,0.0000195001,0.05000,4.999
+24,self_attn.q_proj,0.0000731985,0.05000,5.013
+24,self_attn.o_proj,0.0000015971,0.05000,1.046
+24,mlp.gate_proj,0.0000816732,0.05000,2.348
+24,mlp.up_proj,0.0000576196,0.05000,2.363
+24,mlp.down_proj,0.0000048145,0.05000,2.924
+25,self_attn.v_proj,0.0000157814,0.05000,4.796
+25,self_attn.q_proj,0.0000655517,0.05000,4.887
+25,self_attn.k_proj,0.0000338076,0.05000,4.911
+25,self_attn.o_proj,0.0000018210,0.05000,1.030
+25,mlp.up_proj,0.0000605838,0.05000,2.382
+25,mlp.gate_proj,0.0000865645,0.05000,2.403
+25,mlp.down_proj,0.0000061517,0.05000,2.949
+26,self_attn.k_proj,0.0000397186,0.05000,5.017
+26,self_attn.q_proj,0.0000629629,0.05000,5.040
+26,self_attn.v_proj,0.0000218369,0.05000,5.064
+26,self_attn.o_proj,0.0000021068,0.05000,1.017
+26,mlp.gate_proj,0.0000916392,0.05000,2.277
+26,mlp.up_proj,0.0000632485,0.05000,2.296
+26,mlp.down_proj,0.0000102032,0.05000,2.917
+27,self_attn.v_proj,0.0000139737,0.05000,4.881
+27,self_attn.k_proj,0.0000263273,0.05000,4.936
+27,self_attn.q_proj,0.0000469980,0.05000,4.958
+27,self_attn.o_proj,0.0000071803,0.05000,1.008
+27,mlp.up_proj,0.0000702180,0.05000,2.307
+27,mlp.gate_proj,0.0000891004,0.05000,2.325
+27,mlp.down_proj,0.0000469706,0.05000,2.988

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/hibgcqvy-hpwwspav/",
+    "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"
+}