Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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 +1,14 @@
+{{ bos_token }}
+{%- for message in messages -%}
+{%- if message['role'] == 'assistant' -%}
+    <|start_header_id|>{{ message['role'] }}<|end_header_id|>
+{% generation %}{{- message['content'] | trim }}<|eot_id|>{% endgeneration %}
+
+{% else %}
+<|start_header_id|>{{ message['role'] }}<|end_header_id|>
+{{ message['content'] | trim }}<|eot_id|>
+{% endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|start_header_id|>assistant<|end_header_id|>
+{% endif -%}

config.json

@@ -0,0 +1 @@
+{"vocab_size": 144644, "max_position_embeddings": 4096, "hidden_size": 1024, "intermediate_size": 3072, "num_hidden_layers": 28, "num_attention_heads": 16, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 8, "head_dim": 64, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "layer_types": ["full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention"], "return_dict": true, "output_hidden_states": false, "torchscript": false, "torch_dtype": null, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": ["Qwen3ForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "_name_or_path": "", "transformers_version": "4.55.4", "no_bias": true, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "qwen3", "output_attentions": false}

config.json~

@@ -0,0 +1 @@
+{"vocab_size": 144644, "max_position_embeddings": 4096, "hidden_size": 1024, "intermediate_size": 3072, "num_hidden_layers": 28, "num_attention_heads": 16, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 8, "head_dim": 64, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "layer_types": ["full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention"], "return_dict": true, "output_hidden_states": false, "torchscript": false, "torch_dtype": null, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "_name_or_path": "", "transformers_version": "4.55.4", "no_bias": true, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "qwen3", "output_attentions": false}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5113185dbabd57ae1bcd9a3ad1141f32841f888f75f501dfbe99ef879dd72809
+size 2594493008

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    "<|text_start|>",
+    "<|text_end|>",
+    "<|audio_start|>",
+    "<|audio_end|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c2f8c6c93d178640aabccd2c24b0a45fd2b0e31eb2e550ca6d76767e9dc49c
+size 20167966