Clean repository before upload

.gitattributes

@@ -1,36 +0,0 @@
-*.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

adapter_config.json

@@ -1,44 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.19.1",
-  "qalora_group_size": 16,
-  "r": 64,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "k_proj",
-    "v_proj",
-    "o_proj"
-  ],
-  "target_parameters": [],
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2f5fed994f04a29ee259760ae900b1c61b388ef3c0132044376ecdd6453bc4b
-size 31865104

chat_template.jinja

@@ -1,112 +0,0 @@
-{%- macro render_content(msg) -%}
-    {%- set c = msg.get('content') -%}
-    {%- if c is string -%}
-      {{ c }}
-    {%- elif c is not none -%}
-      {% for content in c -%}
-        {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
-          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
-        {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
-          <|kimi_k25_video_placeholder|>
-        {% else -%}
-          {{ content['text'] }}
-        {%- endif -%}
-      {%- endfor -%}
-    {%- endif -%}
-{%- endmacro -%}
-
-{% macro set_roles(message) -%}
-  {%- set role_name =  message.get('name') or  message['role'] -%}
-  {%- if message['role'] == 'user' -%}
-    <|im_user|>{{role_name}}<|im_middle|>
-  {%- elif message['role'] == 'assistant' -%}
-    <|im_assistant|>{{role_name}}<|im_middle|>
-  {%- else -%}
-    <|im_system|>{{role_name}}<|im_middle|>
-  {%- endif -%}
-{%- endmacro -%}
-
-
-{%- macro render_toolcalls(message) -%}
-  <|tool_calls_section_begin|>
-  {%- for tool_call in message['tool_calls'] -%}
-    {%- set formatted_id = tool_call['id'] -%}
-    <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
-  {%- endfor -%}
-  <|tool_calls_section_end|>
-{%- endmacro -%}
-
-
-{%- set preserve_thinking = preserve_thinking | default(false) -%}
-{# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}
-{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
-{%- if not preserve_thinking -%}
-{%- for idx in range(messages|length-1, -1, -1) -%}
-    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
-        {%- set ns.last_non_tool_call_assistant_msg = idx -%}
-        {%- break -%}
-    {%- endif -%}
-{%- endfor -%}
-{%- endif -%}
-
-{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
-{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
-{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
-
-{%- if tools -%}
-  {%- if tools_ts_str -%}
-    <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>
-  {%- else -%}
-    <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
-  {%- endif -%}
-{%- endif -%}
-
-  
-{%- for message in hist_msgs -%}
-  {{set_roles(message)}}
-  {%- if message['role'] == 'assistant' -%}
-    <think></think>{{render_content(message)}}
-    {%- if message.get('tool_calls') -%}
-      {{render_toolcalls(message)}}
-    {%- endif -%}
-  {%- elif message['role'] == 'tool' -%}
-    {%- set tool_call_id = message.tool_call_id -%}
-    ## Return of {{ tool_call_id }}
-{{render_content(message)}}
-  {%- elif message['content'] is not none -%}
-    {{render_content(message)}}
-  {%- endif -%}
-  <|im_end|>
-{%- endfor -%}
-
-{%- for message in suffix_msgs -%}
-  {{set_roles(message)}}
-  {%- if message['role'] == 'assistant' -%}
-    {%- if thinking is defined and thinking is false and preserve_thinking is false -%}
-    <think></think>{{render_content(message)}}
-    {%- else -%}
-    {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}
-    <think>{{rc}}</think>{{render_content(message)}}
-    {%- endif -%}
-    {%- if message.get('tool_calls') -%}
-     {{render_toolcalls(message)}}
-    {%- endif -%}
-  {%- elif message['role'] == 'tool' -%}
-    {%- set tool_call_id = message.tool_call_id -%}
-    ## Return of {{ tool_call_id }}
-{{render_content(message)}}
-  {%- elif message['content'] is not none -%}
-    {{render_content(message)}}
-  {%- endif -%}
-  <|im_end|>
-{%- endfor -%}
-
-
-{%- if add_generation_prompt -%}
-  <|im_assistant|>assistant<|im_middle|>
-  {%- if thinking is defined and thinking is false -%}
-  <think></think>
-  {%- else -%}
-  <think>
-  {%- endif -%}
-{%- endif -%}

config.json

@@ -1,55 +0,0 @@
-{
-  "architectures": [
-    "DeepseekV3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "aux_loss_alpha": 0.001,
-  "bos_token_id": 163584,
-  "dtype": "bfloat16",
-  "eos_token_id": 163585,
-  "ep_size": 1,
-  "first_k_dense_replace": 1,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 11264,
-  "kv_lora_rank": 512,
-  "max_position_embeddings": 131072,
-  "model_type": "deepseek_v3",
-  "moe_intermediate_size": 1408,
-  "moe_layer_freq": 1,
-  "n_group": 1,
-  "n_routed_experts": 64,
-  "n_shared_experts": 2,
-  "norm_topk_prob": true,
-  "num_attention_heads": 16,
-  "num_experts_per_tok": 6,
-  "num_hidden_layers": 27,
-  "num_key_value_heads": 16,
-  "num_nextn_predict_layers": 1,
-  "num_shared_experts": 2,
-  "pad_token_id": 163839,
-  "pretraining_tp": 1,
-  "q_lora_rank": null,
-  "qk_head_dim": 192,
-  "qk_nope_head_dim": 128,
-  "qk_rope_head_dim": 64,
-  "rms_norm_eps": 1e-05,
-  "rope_interleave": true,
-  "rope_parameters": {
-    "rope_theta": 800000.0,
-    "rope_type": "default"
-  },
-  "routed_scaling_factor": 2.446,
-  "scoring_func": "sigmoid",
-  "seq_aux": true,
-  "tie_word_embeddings": false,
-  "topk_group": 1,
-  "topk_method": "noaux_tc",
-  "transformers_version": "5.8.1",
-  "use_cache": false,
-  "v_head_dim": 128,
-  "vocab_size": 163840
-}

generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 163584,
-  "eos_token_id": 163585,
-  "pad_token_id": 163839,
-  "transformers_version": "5.8.1"
-}

model-00001-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11844c30848c15289a9cc545bb98b578066bc926d4c35443c6b3f9f64a75581d
-size 4996317112

model-00002-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98f7e4b6aec31dd0741d5c04895bcdcb83770cb758f44abfe78b8d1718b3a31c
-size 4699860696

model-00003-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c4f445af2a42b8abb356bd9383db0e42940b68889bcaa417c05027f5bf4cdbe
-size 4678885128

model-00004-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b4181dae1acbaa54e8d2d512f3e0a5e4bee6c6f49479714a9cb97af007eb5075
-size 4678885544

model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:03312ba05824052bc517148fe094a9fcd81c3a3fc88c376bb3481d24a9948855
-size 4678885544

model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7016b61807291e25dc538589601c7960b67ea04afa59cb466219045abb7ee006
-size 4678885544

model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:265c32ba15aadd7b74a7094be82f57ddc058f7e27f7b7e9e58ecb65d26b34d46
-size 3509164048

tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:261590fd5234433c558e867ea7d9b8d8a29ebc6bf51d9d43a9d714e4793db0e9
-size 19545255

tokenizer_config.json

@@ -1,12 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "[BOS]",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "[EOS]",
-  "is_local": true,
-  "local_files_only": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": "[UNK]"
-}