Duplicate from shisa-ai/shisa-v2-llama3.1-405b-W4A16-gs128

Co-authored-by: lhl <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- 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 %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- 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 + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\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 %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- 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 %}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 16384,
+  "initializer_range": 0.02,
+  "intermediate_size": 53248,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 128,
+  "num_hidden_layers": 126,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:2.2.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

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": "4.52.3"
+}

model-00001-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7624c458c474b56d12517e688dc99e949d4f9a82b9bcce7f354d832fbb618bce
+size 4202692752

model-00002-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2273109ebd9c32da07c5896a82fc84ed2d49f0b59e88020ada806f8566034b90
+size 3610157512

model-00003-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69545b23a8d00f9d7f310a30366bfb4b7b587d68c37c4b755af8902d62244d58
+size 3766852704

model-00004-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fbcca1a82ca89d2fca583b8aa795b828b2b4240bc79b75108394ed3f4bbbf1
+size 3766852696

model-00005-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaabe63fa37db61d7077ea3a6bfdab7c2f30bbe490cd878dca69efb41625b4cd
+size 3924157096

model-00006-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a95f6529eb6e8292f1e70aecd3a84cf1adc5c78afb1e60e1b6c2d50b232228
+size 3906379360

model-00007-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe19d6348bb3a292f88ddcd2ceb3d4137d47ab35a212fe968c857fa046b9fff
+size 3766852760

model-00008-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f711a4c2cf3309c26244db0aa00037dccafc46e17749d671105b54e3596b7997
+size 3924157168

model-00009-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dafa31e5fab861e6c827758a6399432368549852c5f2408767ca1f0851bcbe9
+size 3906379376

model-00010-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f661329ba429c12498a9222f4eae8cbe965a19d660370f090e65e70df3badb
+size 3766852760

model-00011-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffef6133eca40965ca7b42213ea9c3f778a42b1ebc9ac6b7dbcf3578514d9764
+size 3924157168

model-00012-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e072defe939da4598732701a1e3e68892b71a132ef554846172d341d53fbc7
+size 3906379376

model-00013-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0fca69d12f2181d015de7f6b2590b938f30c9c12d5e734e41ec969d5af962a
+size 3766852760

model-00014-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94ff5866762e9ddc5f2f1c10636a07e21cc263ece1d32f9a53c8fa8f2fffcfd
+size 3924157168

model-00015-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71876de1934b2cefa9daffaabd32693ce89b0c379ab23d3b84465dad0f6f7851
+size 3906379376

model-00016-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67cd828f99eb67dc22cc6935a4340cce8134cbbf70e2ecc581387d90258ef04
+size 3766852760

model-00017-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4a54c97ef55f0fb236ab73e096a8a19525d4c646f304b82a6799898aa97043
+size 3924157168

model-00018-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a551605f4c687713d9f34ee5b1d4fec3720f926e3a49fede27f7ff16d4a9cd7
+size 3906379376

model-00019-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4b4de3b09ecbf6881e7a2beb993478cec3a8ae66a7b63c061c3b4ba16a5d0f
+size 3766852760

model-00020-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f176a35288a98a68b2c1bc7d9ac72d286191e54d36ef7e7bd90151977e3b503c
+size 3924157168

model-00021-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999f85c7bfb3249856f7cc120634a5479a52abcb44c8fe679a4aaeba07329e95
+size 3906379376

model-00022-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716b2898a85266f32cd950f6841f7860a02dab5f42b5989c65a7bbf6e9649530
+size 3766852760

model-00023-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1464c3f203cc31460c75eed343201520aa9c4c1a5baadbd9e41d12e0f34b253
+size 3924157168

model-00024-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7549bde4e58ea3182553ae621d6e5599ef4c8f5332d39c3a712e0c5330df1e
+size 3906379376

model-00025-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c57f5b8f5b12a43113fcf16fce5421c62d7e166fcb98eecc67ebe8e20bfced4e
+size 3766852760

model-00026-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5ac7fc81c65d701421a8d22f127aad3f1698100f4c080851eac31ae1e80d58
+size 3924157168

model-00027-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c754ac23b4f6bededdac2ff14c96e2d57f0ad5cf94fb49662a3ea6fd62c4d91
+size 3906379376

model-00028-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394f940704410a8e66294ec25e5e6ee8015f4562e0000d91f6b4b3aef832ba5f
+size 3766852760

model-00029-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986276a4d8da96eac622bff6da02a59fc58e86012f773aab22cff383bc4475bf
+size 3924157168

model-00030-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bddbf3292de7f20bc250d1c1aba5c69136fb03cdfe6c6620aeee97978e70332
+size 3906379376

model-00031-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37b2d013cb7335f524f34a58bd29998cc4fc127d38b1d1bd3b4d7830c965646
+size 3766852760

model-00032-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9754f361a12da03cf1fb730f44be80f2f0584961b4b47303b4bcccafb38323
+size 3924157168

model-00033-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6ca5429c799ff298a703c866abbc66919de3ff597d59599bf5b29edb35227b
+size 3906379376

model-00034-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41fe986bf5090094bbcee1d7d5f9bda2cf51f569bdf6703658c0384c89e63fd
+size 3766852760

model-00035-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b7310c8d8da7f63751ee548ec1ade8d9e1438929087aa884e82b7796293168
+size 3924157168

model-00036-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce156be7652fda3125c3af4471a0d6f894dbec82a7b2eb367315a02b80cdabc
+size 3906379376

model-00037-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7874dbad8f3137d75dfd60127f23a2f7c140e362ac6007dd8bbe8b5396f24677
+size 3766852760

model-00038-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fff1444be87828a8631a44da7b4ff42e91e6d01faf7ae59c41e03d641d3138
+size 3924157168

model-00039-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b9603e2cc096803d7667c28f9ee1f96a63bc29d0e22faab314de3cb38892b5
+size 3906379376

model-00040-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f73fd88f37eb3e9db30b9627185ba8760a14f824797af038f81ffe75359e88
+size 3766852760

model-00041-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489e5f6f31f540213fe21e8307e77aa4418b8cecb4eb1497e63f71ce631add91
+size 3924157168

model-00042-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f65690c49179c1376e98030cf1816c5ef612a9413e2697207229cc28b63204
+size 3906379376

model-00043-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9131b19fd4bcd5b711d4261d326d7ffad2583f47614ab60ec4308938a5fa8d28
+size 3766852760

model-00044-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310e7f7a2742f63294d8cfa3d7b28392354b7e2c6103ef1e0c97744a102bd8e3
+size 3924157160

model-00045-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46f9c4cac9404020d6ff75f21a08ee333d96f59ac21662c9af6aaf6d10f26aa
+size 3906379448

model-00046-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113193c3f0939f49a2ec944072a6ad1ac688d70b279ffc02ec09b552993f7170
+size 3766852824