初始化项目，由ModelHub XC社区提供模型

Model: Cheng98/llama-39m
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,79 @@
+---
+license: llama2
+---
+
+# Toy LLaMA-39M
+
+- This is a tiny LLaMA model pretrained on [Recag/Rp_C4_55](https://huggingface.co/datasets/Recag/Rp_C4_55), a small subset of C4 with `seq_len=512`.
+  - Model architecture
+      ```json
+      {
+        "hidden_size": 512,
+        "intermediate_size": 2048,
+        "max_position_embeddings": 2048,
+        "num_attention_heads": 8,
+        "num_hidden_layers": 2,
+        "num_key_value_heads": 8
+      }
+      ```
+  - Load model and tokenizer:
+      ```python
+      from transformers import AutoTokenizer, AutoModelForCausalLM
+      model = AutoModelForCausalLM.from_pretrained("Cheng98/llama-39m")
+      tokenizer = AutoTokenizer.from_pretrained("Cheng98/llama-39m")
+      ```
+  - Training script: [huggingface/transformers/examples/pytorch/language-modeling/run_clm.py](https://github.com/huggingface/transformers/blob/e9476832942a19cf99354776ef112babc83c139a/examples/pytorch/language-modeling/run_clm.py)
+      ```python
+      # "train" split is created from the last 95% samples of original "train" subset
+      raw_datasets["validation"] = load_dataset("Recag/Rp_C4_55", split="train[5%:]")
+      ```
+
+
+- Evaluation (`seq_len=512`):
+   
+  | Dataset        | Eval loss | Perplexity | Accuracy | block_size |
+  |----------------|-----------|------------|----------|------------|
+  | Recag/Rp_C4_55 | 3.63      | 37.78      | 0.3561   | 512        |
+  | Wikitext2      | 4.58      | 97.48      | 0.2719   | 512        |
+
+  - Evaluation command (Wikitext2):
+      ```bash
+      # Evaluation command
+      python run_clm.py --model_name_or_path Cheng98/llama-39m \
+        --dataset_name wikitext \
+        --dataset_config_name wikitext-2-raw-v1 \
+        --block_size 512 \
+        --do_eval \
+        --output_dir ./results
+      ```
+  
+  - Evaluation on Recag/Rp_C4_55 (`seq_len=512`):
+      ```python
+      # "validation" split is created from the first 5% samples of original "train" subset
+      raw_datasets["validation"] = load_dataset("Recag/Rp_C4_55", split="train[:5%]")
+      ```
+      Results
+      ```json
+      {
+        "eval_accuracy": 0.3561766818954313,
+        "eval_loss": 3.6318140029907227,
+        "eval_runtime": 190.8411,
+        "eval_samples": 19413,
+        "eval_samples_per_second": 101.723,
+        "eval_steps_per_second": 1.593,
+        "perplexity": 37.7812898658763
+      }
+      ```
+      
+  - Evaluation on Wikitext2 (`seq_len=512`):
+      ```json
+      {
+        "eval_accuracy": 0.2718795201225219,
+        "eval_loss": 4.579628944396973,
+        "eval_runtime": 3.939,
+        "eval_samples": 575,
+        "eval_samples_per_second": 145.976,
+        "eval_steps_per_second": 0.762,
+        "perplexity": 97.47821765687856
+      }
+      ```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "checkpoints/toy-llama-39m/checkpoint-86428",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25068ff4686ca9f8d2dfc881065f7d588df801fb19e130ebad3d5f289e707188
+size 164638984

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}