初始化项目，由ModelHub XC社区提供模型

Model: MEME-KING16/granite-3.2-8b-claude-opus-full-ft
Source: Original Platform

checkpoint-100/chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
+' + message['content'] + '<|im_end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
+' + message['content'] + '<|im_end|>
+' }}{% else %}{{ '<|im_start|>system
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-100/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 49155,
+  "dtype": "bfloat16",
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_name": "unsloth/granite-3.2-8b-instruct",
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 4,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.3.3",
+  "use_cache": false,
+  "vocab_size": 49155
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 49155,
+  "eos_token_id": [
+    0
+  ],
+  "max_length": 131072,
+  "pad_token_id": 4,
+  "transformers_version": "5.2.0"
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d2c8c2d34c590f1c429a1bad529d2ccac25f8e5fe04f8e70cdb93974dbfd14
+size 16341738952

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80b6e70b49824132c638d32166dd4a73eaad68fa13dab43adff1f6b1a0c91df
+size 32683715489

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f8b6881a432bd2506b4c142d6f9b7b6b337d2665d39a90b132dcb1c80cdc27
+size 1465

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|end_of_text|>",
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<fim_pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7590132827324478,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07590132827324478,
+      "grad_norm": 22.0,
+      "learning_rate": 9e-08,
+      "loss": 1.0496648788452148,
+      "step": 10
+    },
+    {
+      "epoch": 0.15180265654648956,
+      "grad_norm": 21.5,
+      "learning_rate": 1.8999999999999998e-07,
+      "loss": 1.0672600746154786,
+      "step": 20
+    },
+    {
+      "epoch": 0.22770398481973433,
+      "grad_norm": 23.375,
+      "learning_rate": 2.9e-07,
+      "loss": 1.074104118347168,
+      "step": 30
+    },
+    {
+      "epoch": 0.3036053130929791,
+      "grad_norm": 19.0,
+      "learning_rate": 3.8999999999999997e-07,
+      "loss": 1.0784456253051757,
+      "step": 40
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "grad_norm": 21.25,
+      "learning_rate": 4.9e-07,
+      "loss": 1.0631229400634765,
+      "step": 50
+    },
+    {
+      "epoch": 0.45540796963946867,
+      "grad_norm": 18.625,
+      "learning_rate": 5.9e-07,
+      "loss": 1.0021364212036132,
+      "step": 60
+    },
+    {
+      "epoch": 0.5313092979127134,
+      "grad_norm": 19.625,
+      "learning_rate": 6.9e-07,
+      "loss": 1.0368730545043945,
+      "step": 70
+    },
+    {
+      "epoch": 0.6072106261859582,
+      "grad_norm": 13.1875,
+      "learning_rate": 7.9e-07,
+      "loss": 0.9585152626037597,
+      "step": 80
+    },
+    {
+      "epoch": 0.683111954459203,
+      "grad_norm": 10.4375,
+      "learning_rate": 8.9e-07,
+      "loss": 0.8780872344970703,
+      "step": 90
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.9e-07,
+      "loss": 0.8695860862731933,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 396,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.816482044765798e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c046e33cd8fc19c158792bb00b2580a5dcc0c5b7d92fa961dea01e4c3b0aa96
+size 5585