Upload folder using huggingface_hub

chat_template.jinja

@@ -1,3 +1,4 @@
+{# Unsloth template fixes #}
 {%- macro render_content(msg) -%}
     {%- set c = msg.get('content') -%}
     {%- if c is string -%}
@@ -48,8 +49,8 @@
 {%- 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 -%}
-  <|im_system|>tool_declare<|im_middle|>{{ tools | tojson | replace(', ', ',') | replace(': ', ':') }}<|im_end|>
+{%- if tools -%}{%- set tools_json = tools|tojson -%}{%- set tools_json = tools_json.split(': ') | join(':') -%}{%- set tools_json = tools_json.split(', ') | join(',') -%}
+  <|im_system|>tool_declare<|im_middle|>{{ tools_json }}<|im_end|>
 {%- endif -%}
 
 {%- for message in hist_msgs -%}
@@ -93,4 +94,5 @@
 
 {%- if add_generation_prompt -%}
   <|im_assistant|>assistant<|im_middle|>
-{%- endif -%}
+{%- endif -%}
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

config.json

@@ -1,7 +1,5 @@
 {
   "_attn_implementation_autoset": false,
-  "_name_or_path": "",
-  "add_cross_attention": false,
   "architectures": [
     "DeepseekV3ForCausalLM"
   ],
@@ -13,66 +11,31 @@
     "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "aux_loss_alpha": 0.001,
-  "bad_words_ids": null,
-  "begin_suppress_tokens": null,
   "bos_token_id": 163584,
-  "chunk_size_feed_forward": 0,
-  "cross_attention_hidden_size": null,
-  "decoder_start_token_id": null,
-  "diversity_penalty": 0.0,
-  "do_sample": false,
-  "early_stopping": false,
-  "encoder_no_repeat_ngram_size": 0,
+  "torch_dtype": "bfloat16",
   "eos_token_id": 163586,
   "ep_size": 1,
-  "exponential_decay_length_penalty": null,
-  "finetuning_task": null,
   "first_k_dense_replace": 1,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
   "hidden_act": "silu",
   "hidden_size": 7168,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 18432,
-  "is_decoder": false,
-  "is_encoder_decoder": false,
   "kv_lora_rank": 512,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
-  "length_penalty": 1.0,
-  "max_length": 20,
   "max_position_embeddings": 262144,
-  "min_length": 0,
-  "model_type": "kimi_k2",
+  "model_type": "deepseek_v3",
   "moe_intermediate_size": 2048,
   "moe_layer_freq": 1,
   "n_group": 1,
   "n_routed_experts": 384,
   "n_shared_experts": 1,
-  "no_repeat_ngram_size": 0,
   "norm_topk_prob": true,
   "num_attention_heads": 64,
-  "num_beam_groups": 1,
-  "num_beams": 1,
   "num_experts_per_tok": 8,
   "num_hidden_layers": 61,
   "num_key_value_heads": 64,
   "num_nextn_predict_layers": 0,
-  "num_return_sequences": 1,
-  "output_attentions": false,
-  "output_hidden_states": false,
-  "output_scores": false,
   "pad_token_id": 163839,
-  "prefix": null,
   "pretraining_tp": 1,
-  "problem_type": null,
-  "pruned_heads": {},
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
@@ -109,10 +72,6 @@
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed"
   },
-  "remove_invalid_values": false,
-  "repetition_penalty": 1.0,
-  "return_dict": true,
-  "return_dict_in_generate": false,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "beta_fast": 1.0,
@@ -126,24 +85,12 @@
   "rope_theta": 50000.0,
   "routed_scaling_factor": 2.827,
   "scoring_func": "sigmoid",
-  "sep_token_id": null,
   "seq_aux": true,
-  "suppress_tokens": null,
-  "task_specific_params": null,
-  "temperature": 1.0,
-  "tf_legacy_loss": false,
-  "tie_encoder_decoder": false,
   "tie_word_embeddings": false,
-  "tokenizer_class": null,
-  "top_k": 50,
-  "top_p": 1.0,
   "topk_group": 1,
   "topk_method": "noaux_tc",
-  "torch_dtype": "bfloat16",
-  "torchscript": false,
-  "transformers_version": "4.51.3",
-  "typical_p": 1.0,
-  "use_bfloat16": false,
+  "transformers_version": "4.57.1",
+  "unsloth_fixed": true,
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 163840

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "[EOT]",
+    "<|im_system|>",
+    "<|im_middle|>"
+  ],
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -163,18 +163,20 @@
     "<|im_system|>",
     "<|im_middle|>"
   ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_kimi.TikTokenTokenizer",
+      null
+    ]
+  },
   "bos_token": "[BOS]",
   "clean_up_tokenization_spaces": false,
   "eos_token": "[EOS]",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 262144,
   "pad_token": "[PAD]",
+  "padding_side": "left",
   "tokenizer_class": "TikTokenTokenizer",
   "unk_token": "[UNK]",
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_kimi.TikTokenTokenizer",
-      null
-    ]
-  }
+  "chat_template": "{# Unsloth template fixes #}\n{%- macro render_content(msg) -%}\n    {%- set c = msg.get('content') -%}\n    {%- if c is string -%}\n      {{ c }}\n    {%- elif c is not none -%}\n      {% for content in c -%}\n        {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n          <|media_start|>image<|media_content|><|media_pad|><|media_end|>\n        {% else -%}\n          {{ content['text'] }}\n        {%- endif -%}\n      {%- endfor -%}\n    {%- endif -%}\n{%- endmacro -%}\n\n{% macro set_roles(message) -%}\n  {%- set role_name =  message.get('name') or  message['role'] -%}\n  {%- if message['role'] == 'user' -%}\n    <|im_user|>{{role_name}}<|im_middle|>\n  {%- elif message['role'] == 'assistant' -%}\n    <|im_assistant|>{{role_name}}<|im_middle|>\n  {%- else -%}\n    <|im_system|>{{role_name}}<|im_middle|>\n  {%- endif -%}\n{%- endmacro -%}\n\n\n{%- macro render_toolcalls(message) -%}\n  <|tool_calls_section_begin|>\n  {%- for tool_call in message['tool_calls'] -%}\n    {%- set formatted_id = tool_call['id'] -%}\n    <|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|>\n  {%- endfor -%}\n  <|tool_calls_section_end|>\n{%- endmacro -%}\n\n\n{# Find last non-tool-call assisitant message #}\n{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}\n{%- for idx in range(messages|length-1, -1, -1) -%}\n    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}\n        {%- set ns.last_non_tool_call_assistant_msg = idx -%}\n        {%- break -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}\n{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}\n{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}\n\n{%- if tools -%}{%- set tools_json = tools|tojson -%}{%- set tools_json = tools_json.split(': ') | join(':') -%}{%- set tools_json = tools_json.split(', ') | join(',') -%}\n  <|im_system|>tool_declare<|im_middle|>{{ tools_json }}<|im_end|>\n{%- endif -%}\n\n{%- for message in hist_msgs -%}\n  {%- if loop.first and messages[0]['role'] != 'system' -%}\n  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>\n  {%- endif -%}\n  {{set_roles(message)}}\n  {%- if message['role'] == 'assistant' -%}\n    <think></think>{{render_content(message)}}\n    {%- if message.get('tool_calls') -%}\n      {{render_toolcalls(message)}}\n    {%- endif -%}\n  {%- elif message['role'] == 'tool' -%}\n    {%- set tool_call_id = message.tool_call_id -%}\n    ## Return of {{ tool_call_id }}\n{{render_content(message)}}\n  {%- elif message['content'] is not none -%}\n    {{render_content(message)}}\n  {%- endif -%}\n  <|im_end|>\n{%- endfor -%}\n\n{%- for message in suffix_msgs -%}\n  {{set_roles(message)}}\n  {%- if message['role'] == 'assistant' -%}\n    {%- set rc = message.get('reasoning_content', '') -%}\n    <think>{{rc}}</think>{{render_content(message)}}\n    {%- if message.get('tool_calls') -%}\n     {{render_toolcalls(message)}}\n    {%- endif -%}\n  {%- elif message['role'] == 'tool' -%}\n    {%- set tool_call_id = message.tool_call_id -%}\n    ## Return of {{ tool_call_id }}\n{{render_content(message)}}\n  {%- elif message['content'] is not none -%}\n    {{render_content(message)}}\n  {%- endif -%}\n  <|im_end|>\n{%- endfor -%}\n\n\n{%- if add_generation_prompt -%}\n  <|im_assistant|>assistant<|im_middle|>\n{%- endif -%}\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
 }