初始化项目，由ModelHub XC社区提供模型

Model: nkasmanoff/nature-buddy
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+nature-buddy-0.135b-f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-0.5B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: nature-buddy
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# nature-buddy
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.254602634660147e+16,
+    "train_loss": 0.7783217168792965,
+    "train_runtime": 2040.3082,
+    "train_samples_per_second": 12.444,
+    "train_steps_per_second": 1.556
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e643770bce343c270006afd6b162439100bad9b89834fba81ec318e1bd5c944
+size 269060552

nature-buddy-0.135b-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0c066bfe3a37034974f7cdb30421405d84ff10191cdc298cc8a1684ee6cacb
+size 270885664

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.254602634660147e+16,
+    "train_loss": 0.7783217168792965,
+    "train_runtime": 2040.3082,
+    "train_samples_per_second": 12.444,
+    "train_steps_per_second": 1.556
+}

trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 3175,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 5.84375,
+      "learning_rate": 0.00031446540880503143,
+      "loss": 1.6016,
+      "step": 100
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 2.90625,
+      "learning_rate": 0.0004997720451762572,
+      "loss": 2.0478,
+      "step": 200
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 3.0,
+      "learning_rate": 0.0004973084374349976,
+      "loss": 2.0072,
+      "step": 300
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.0004921639131931859,
+      "loss": 1.8507,
+      "step": 400
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 1.6953125,
+      "learning_rate": 0.00048439424102900066,
+      "loss": 1.7019,
+      "step": 500
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00047408364711169396,
+      "loss": 1.5988,
+      "step": 600
+    },
+    {
+      "epoch": 1.1023622047244095,
+      "grad_norm": 1.8203125,
+      "learning_rate": 0.00046134390215823,
+      "loss": 1.3103,
+      "step": 700
+    },
+    {
+      "epoch": 1.2598425196850394,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.00044631310979666443,
+      "loss": 1.237,
+      "step": 800
+    },
+    {
+      "epoch": 1.4173228346456692,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0004291542094708612,
+      "loss": 1.2112,
+      "step": 900
+    },
+    {
+      "epoch": 1.574803149606299,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.000410053210115622,
+      "loss": 1.1948,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7322834645669292,
+      "grad_norm": 1.5859375,
+      "learning_rate": 0.00038921717374985584,
+      "loss": 1.1666,
+      "step": 1100
+    },
+    {
+      "epoch": 1.889763779527559,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.0003668719708463959,
+      "loss": 1.1001,
+      "step": 1200
+    },
+    {
+      "epoch": 2.047244094488189,
+      "grad_norm": 1.6171875,
+      "learning_rate": 0.00034325983181110047,
+      "loss": 0.9377,
+      "step": 1300
+    },
+    {
+      "epoch": 2.204724409448819,
+      "grad_norm": 1.640625,
+      "learning_rate": 0.00031863672111412524,
+      "loss": 0.6561,
+      "step": 1400
+    },
+    {
+      "epoch": 2.362204724409449,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00029326956253877123,
+      "loss": 0.6872,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5196850393700787,
+      "grad_norm": 1.5859375,
+      "learning_rate": 0.00026743334562725617,
+      "loss": 0.6448,
+      "step": 1600
+    },
+    {
+      "epoch": 2.677165354330709,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.00024140814469062377,
+      "loss": 0.643,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8346456692913384,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002154760826978469,
+      "loss": 0.6216,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9921259842519685,
+      "grad_norm": 1.625,
+      "learning_rate": 0.00018991827295670777,
+      "loss": 0.5788,
+      "step": 1900
+    },
+    {
+      "epoch": 3.1496062992125986,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00016501177173978493,
+      "loss": 0.2589,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3070866141732282,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.00014102657489022886,
+      "loss": 0.2383,
+      "step": 2100
+    },
+    {
+      "epoch": 3.4645669291338583,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00011822269096524812,
+      "loss": 0.2227,
+      "step": 2200
+    },
+    {
+      "epoch": 3.622047244094488,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.684732264553247e-05,
+      "loss": 0.2168,
+      "step": 2300
+    },
+    {
+      "epoch": 3.779527559055118,
+      "grad_norm": 1.0390625,
+      "learning_rate": 7.713218696519558e-05,
+      "loss": 0.2162,
+      "step": 2400
+    },
+    {
+      "epoch": 3.937007874015748,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.929100341195187e-05,
+      "loss": 0.1944,
+      "step": 2500
+    },
+    {
+      "epoch": 4.094488188976378,
+      "grad_norm": 0.45703125,
+      "learning_rate": 4.351717712746703e-05,
+      "loss": 0.123,
+      "step": 2600
+    },
+    {
+      "epoch": 4.251968503937007,
+      "grad_norm": 0.4609375,
+      "learning_rate": 2.9981702322862735e-05,
+      "loss": 0.0768,
+      "step": 2700
+    },
+    {
+      "epoch": 4.409448818897638,
+      "grad_norm": 0.59375,
+      "learning_rate": 1.8831308637139e-05,
+      "loss": 0.0761,
+      "step": 2800
+    },
+    {
+      "epoch": 4.566929133858268,
+      "grad_norm": 0.53515625,
+      "learning_rate": 1.0186870532686742e-05,
+      "loss": 0.0786,
+      "step": 2900
+    },
+    {
+      "epoch": 4.724409448818898,
+      "grad_norm": 0.640625,
+      "learning_rate": 4.1420969706420505e-06,
+      "loss": 0.0758,
+      "step": 3000
+    },
+    {
+      "epoch": 4.881889763779528,
+      "grad_norm": 0.515625,
+      "learning_rate": 7.625155704936715e-07,
+      "loss": 0.0792,
+      "step": 3100
+    },
+    {
+      "epoch": 5.0,
+      "step": 3175,
+      "total_flos": 2.254602634660147e+16,
+      "train_loss": 0.7783217168792965,
+      "train_runtime": 2040.3082,
+      "train_samples_per_second": 12.444,
+      "train_steps_per_second": 1.556
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.254602634660147e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f433f351c2c965fecc2fe70b61223b0564888c0bdec28eb71603f31ae78ca2a
+size 5432