初始化项目，由ModelHub XC社区提供模型

Model: pvlabs/Chytrej2-90M-Base
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 +1,60 @@
+---
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- llama
+- causal-lm
+- pretrained
+- chytrej
+- base
+library_name: transformers
+datasets:
+- HuggingFaceFW/fineweb-edu
+---
+
+# Chytrej2-90M-Base
+
+A fully custom pretrained language model built from scratch on the LLaMA architecture trained on [FineWeb Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) dataset.
+
+Built by [PingVortex Labs](https://github.com/PingVortexLabs).
+
+[![Discord](https://img.shields.io/badge/Discord-5865F2?logo=discord&logoColor=white)](https://discord.gg/5SzkjVJBs2)
+
+---
+
+## Model Details
+
++ **Parameters:** 90M
++ **Context length:** 8,192 tokens
++ **Language:** English only
++ **Format:** Base model
++ **Architecture:** LLaMA
++ **License:** Apache 2.0
+
+---
+
+## Benchmarks
+
++ No benchmarks - at this scale the benchmarks are more random than based on what the model has learned - we got a checkpoint 55k get better arc easy score than the final model.
+
+---
+
+## Usage
+
+```python
+from transformers import LlamaForCausalLM, PreTrainedTokenizerFast
+
+model = LlamaForCausalLM.from_pretrained("pvlabs/Chytrej2-90M-Base")
+tokenizer = PreTrainedTokenizerFast.from_pretrained("pvlabs/Chytrej2-90M-Base")
+
+prompt = "The capital of France is"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100, repetition_penalty=1.3)
+print(tokenizer.decode(outputs[0]))
+```
+
+---
+
+*Made by [PingVortex](https://pingvortex.com).*

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1376,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.3.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed8e2a3321a6076fbe6de6051fef827e3dc75a3762ec73c223ad5399159fefc
+size 172040976

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|endoftext|>",
+    "<|padding|>"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}