Upload folder using huggingface_hub

chat_template.json

@@ -0,0 +1,91 @@
+{%- if not add_generation_prompt is defined -%}
+    {%- set add_generation_prompt = false -%}
+{%- endif -%}
+
+{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {% set ns.system_prompt = ns.system_prompt + message['content'] %}
+            {% set ns.is_first_sp = false %}
+        {%- else %}
+            {% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+
+{# --- Append tool descriptions if tools are defined --- #}
+{% if tools is defined and tools is not none %}
+    {% set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. '
+        'When a tool call is needed, you MUST use the following format to issue the call:\n'
+        '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n'
+        '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n'
+        'Make sure the JSON is valid.'
+        '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
+    {% for tool in tools %}
+        {% set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
+    {% endfor %}
+    {% set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
+{% endif %}
+
+{{- bos_token -}}{{- ns.system_prompt -}}
+
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_first = false -%}
+        {%- set ns.is_last_user = true -%}
+        {{'<｜User｜>' + message['content'] + '<｜Assistant｜>'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>'}}
+        {%- endif %}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_output_first = true %}
+        {%- for tool in message['tool_calls'] %}
+            {%- set formatted_args = tool['function']['arguments'] if tool['function']['arguments'] is string else tool['function']['arguments']|tojson %}
+            {%- if not ns.is_first %}
+                {%- if message['content'] is none %}
+                    {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + formatted_args + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                {%- else %}
+                    {{- message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + formatted_args + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                {%- endif %}
+                {%- set ns.is_first = true -%}
+            {%- else %}
+                {{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + formatted_args + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+            {%- endif %}
+        {%- endfor %}
+        {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}
+            {%- set ns.is_tool = false -%}
+        {%- else %}
+            {% set content = message['content'] %}
+            {{- content + '<｜end▁of▁sentence｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false -%}
+        {%- set ns.is_tool = true -%}
+        {%- if ns.is_output_first %}
+            {{- 'Use the results below to formulate an answer to the user question unless additional information is needed.' }}
+            {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}
+            {%- set ns.is_output_first = false %}
+        {%- else %}
+            {{- '\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+
+{% if ns.is_tool %}
+    {{- '<｜tool▁outputs▁end｜>'}}
+{% endif %}
+{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}
+    {{- '<｜Assistant｜>' -}}
+{% endif %}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19659b7a6c1a86937f19d9d88c6b565eeb02fbe6cc1acf378e18bf9561e0287
+size 5234141992

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a804b44c5ac3389da1b6dac8268d87e7c212e6693f22ffefa371e5f2a1df012a
+size 4302381728

model-00003-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299320cae3b580caf307f4a73967fe673ef8bfc40031c35bd2ffee8a7e7b17b7
+size 4302382136

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f276f72b1da290d6bc153c155abd949909f72d6cf746109ae59fa9915eac12af
+size 4302347768

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e85e8cf9a2b9bdfc0471d9114fcf0170859e846c8d754b27814f4e214a71bd1
+size 4302381912

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91d33e584ea09abe325c9362ac7a3db1ca6a59f96e9f1b135a818a045a0444f
+size 4372096432

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49c2e21c4b83443873bdc40359bff17bc7a23301273e53fa7031feee618ff3e
+size 4306052768

model-00008-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac59c7ca8ae30fa0075e290bc2b1b86f831af072046a7d80c80bff1fd952e84d
+size 4302382120

model-00009-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cde10c10ef63d25cf8c41a8598600eb0681220a2c19bbc0bb327e32bc254aa
+size 4302347960

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fadceae8522ecfdcf6c535e14f8cf0d15f18073297efcfcb22baad6c345fa2
+size 4302381720

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1d27d2b1494c6eefcc264328caa425f8da2399d6630440d8d5ca6f0d44416c
+size 4302382136

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52d7c6bfe1bdc273694f5f0f57650d122ee808b37e79078754da71a89a41687
+size 1321579568

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec12ec622f7ef7aa876a42a4e48d80172c2d2d6d0b1c3a1de32f1e3ac214091e
+size 4302318704

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4582689adaaad9664f069b06f711f52a8e18771b6a790766d600fd9373e7ad39
+size 4302382088

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2adadb0325377457a8a0ccefe5aa6b1dd9769df39c1a05c3ee8731c9413b305a
+size 4302347992

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8963a67ca7ee4aaf51e415c97c6bf7047edd8a71443b15991fd0aa440391f142
+size 4302381688

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6fa95efaa319a6bc8e00da5974b3c297f4abc9ef400b3f4765b6e52788608a
+size 4302382136

model-00018-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eb0705fe4167ebbf1240089bbbb4ac5549c3495e70b212cf29583b76085498
+size 4302347800

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7c4f285f3df5c3ba6a787a1adc9c8e385b5343a03df6d7df530279efebd7cd
+size 4302381880

model-00020-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9212c79d0084dd81e7791c177557129b0a33769e60365ed86766eb27d471b360
+size 4302382136

model-00021-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ba3e481133dfa92a991522ee1da50ed5b79743cbe61139913707402b51e81a
+size 4302348168

model-00022-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c30f8cd47d592d9e6ec6a80397de015605fe47e21eb4f51f05596baa603156d
+size 4302382664

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413e45a65d6e76a789bbf2f1d448d08e1220710fb141087012106266124ac25e
+size 4302348576

model-00024-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ae0b656a4585e86b1ac420db1d0972d4aea4a52b638e69ec5ebb265cbee12c
+size 4302382264

model-00025-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a771ee5a04de66b683c6d45118ae59f4d0fc77abbf6ed1be4ccb0a7a35c1fd
+size 4302382720

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e420a03202f2553b439cf5f357276325d4218d85bed1332bce3769fcbe6f9c5
+size 4302348392

model-00027-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ffeff7662775ba7497369e4344521b5f1696dc3ea593a279850600e2b67c84
+size 4302382448

model-00028-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e405955ecc3c3a56776629ea55a7a31b49bd31bc190dbbb43e526f2038769ff5
+size 4302382720

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cc8761d14b6cc7fea00613ed35fb0dda47c409248e080e36692f371e05b991
+size 4302348200

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbb117dfb0e9bb7a74a0a488ccd5e234b7403f7f08593b1b948af07a2dcc498
+size 4302382640

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bf552913f63ca2579761162fd9a5a31db58ed0d68b331af55fe1f7ac1404db
+size 4302348600

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28872554fdd36f461ff0aad745b370faf96c3a433d5e6888440cf8f50c7468c
+size 4302382248

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c54b191a962ca6e8b1fc16d7ba11793c5af32b88f1595c7425c835992de141
+size 4302382720

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706b00136ac4a12becfbd34a4c6b2e2c84bbeb44cd1a98ce109587251ccf9e1d
+size 1747412864

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85843407678f9811f56b48c5adf86677ddcb366fb8e7d5731b0da6bd9f7258c
+size 4302319280

model-00036-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3432985323d9c9c068621de200bce2047f1e6f648c809d8909d026af34e77ab
+size 4302382672

model-00037-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1f382a65746a0ad186df222cd8cd21b6aa914a0de8eccc77656af3d8e37ec8
+size 4302348568

model-00038-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8e9b0eabce6b7382641ea629350fba68cb2dbc8ca9388b4e28bdf5048c12b3
+size 4302382280

model-00039-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6712a37ee0f7c640dc27b263d708275589975ddc7909fd3103653d3fdee5830
+size 4302382720

model-00040-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fc58e562ba7eadaf6618d381c135f9f35bfd444512bf65892ebc58adc38a29
+size 4302348376

model-00041-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429316ed86cc8282cd662e0a66490a27ce2e007c36f5cdbef9f81724c5741378
+size 4302382464

model-00042-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56622f2bad1b7117978ebc1c685d418191a5a85032493d579d2f15b450818d36
+size 4302382720

model-00043-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281e52440bd6306ca2e7e0fe7396fa713a68f9ff7b3321fbcf9e243ac13fb5ef
+size 4302348184

model-00044-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76067fab026393e35403b85b09b09790e3fc089c4077dc337f5445c57681c091
+size 4302382664

model-00045-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1936bc9e4aa70b339b84348f31b9cbf996690421f1de7359dbdaa8f6517e21a7
+size 4302348576

model-00046-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a273270cc7f32c7a95010748d8c1f808d933198d3cefdef1da43a24ee91e9e1a
+size 4302382264

model-00047-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a078a594bcae2ed1000f14f6c28a284a2c788f753fa0a56d8a9f25f0bbe34e
+size 4302382720

model-00048-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870e41c61b25555c8af229e2b1d3e1e20bd56a3a52f74147355d0d7f2e26140b
+size 4302348392