初始化项目，由ModelHub XC社区提供模型

Model: Ba2han/model-sft-q
Source: Original Platform

last-checkpoint/chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'].strip() + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

last-checkpoint/config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50030,
+  "dtype": "bfloat16",
+  "eos_token_id": 50031,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 8192,
+  "max_window_layers": 40,
+  "model_name": "Ba2han/qwen-test-3-longer-2",
+  "model_type": "qwen3",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 50034,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "unsloth_version": "2026.3.17",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 50048
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50030,
+  "eos_token_id": [
+    50031
+  ],
+  "max_length": 8192,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 50034,
+  "transformers_version": "5.2.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8914d86370d7da6c973c06e92367ef2d1b75a273a1b15db478cb2d18c913501e
+size 1310251320

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b71903e03b6e910f51c7eb1326c36a00ab07bf20dcd46de20fb9ff12fd0fa8
+size 1675837389

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8dce50b008d0814732d498cb9bb7c93c817a2037afe271ad4d913c29ddd867c
+size 14709

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400735dc8844bbf38dfbf3ec3db60ee3b6bf22f3c4165de387d81e27e8f11adf
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9438ebba5ad881e3f35f6ef6f29325006db6da502f051e05cefadca094da47b2
+size 5713