初始化项目，由ModelHub XC社区提供模型

Model: rkaluzny/CLoverT1-0.03B-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 +1,82 @@
+---
+license: apache-2.0
+language:
+- en
+datasets:
+- Skylion007/openwebtext
+- Salesforce/wikitext
+pipeline_tag: text-generation
+model_size: 33M
+---
+# CLover T1 0.03B (Base)
+
+CLover T1 (or Chat Lover Transformer v1) is a small-scale causal language model designed for efficient text generation and experimentation with compact transformer architectures.
+
+This model represents the base pretraining stage and is intended as a foundation for further instruction tuning and architectural exploration.
+
+---
+
+## Model Overview
+
+- Model size: ~33M parameters
+- Architecture: GPT-style decoder-only transformer
+- Context length: 512 tokens
+- Vocabulary: BPE Tokenizer
+
+This version uses a traditional transformer architecture without modern enhancements such as SwiGLU feed-forward networks or rotary positional embeddings.
+
+---
+
+## Intended Use
+
+This model is suitable for:
+
+- Text continuation
+- Basic conversational experiments
+- Research on small language model behavior
+- Prototyping instruction-tuning pipelines
+
+It is not instruction-tuned and does not consistently follow user commands in a chat-like manner.
+
+---
+
+## Limitations
+
+Because this is a base pretrained model:
+
+- It may produce vague or incomplete answers
+- It does not reliably follow instructions
+- It can lose coherence in longer outputs
+- It may generate repetitive or inconsistent text
+
+These limitations are expected for a model at this scale and training stage.
+
+---
+
+## How to Use
+
+You can load and run the model using Hugging Face Transformers:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_name = "rkaluzny/CLoverT1-0.03B-Base"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+prompt = "What is machine learning?"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    temperature=0.7,
+    top_k=50,
+    top_p=0.9,
+    repetition_penalty=1.2,
+    do_sample=True,
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

config.json

@@ -0,0 +1,20 @@
+{
+  "_name_or_path": "CLoverT1-0.03B-Base",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "model_type": "gpt2",
+  "vocab_size": 30000,
+  "n_positions": 512,
+  "n_embd": 384,
+  "n_layer": 6,
+  "n_head": 6,
+  "n_inner": 1536,
+  "activation_function": "gelu_new",
+  "resid_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "eos_token_id": null,
+  "transformers_version": "4.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465410cb13688b627fea42931cc759c20c8870545cd94affa967d74825c09bdf
+size 135544288