初始化项目，由ModelHub XC社区提供模型

Model: StarpowerTechnology/BbyWVY-360m
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 +1,93 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+pipeline_tag: text-generation
+tags:
+- text-generation
+- conversational
+- smollm2
+- wvy
+- safetensors
+language:
+- en
+library_name: transformers
+---
+
+# BbyWVY-360m
+
+BbyWVY-360m is an experimental conversational language model based on
+`HuggingFaceTB/SmolLM2-360M-Instruct`.
+
+This checkpoint was first instruction-tuned for the WVY chat identity and then
+continued-pretrained on a user-provided, user-message-only corpus. Assistant
+messages and raw training data are not included in this repository.
+
+## Intended Behavior
+
+WVY is tuned to be conversational, curious, and uncertainty-aware:
+
+- admit when it does not know something deeply
+- ask useful follow-up questions
+- build conclusions from what the user explains
+- ask for verification instead of acting like it knows everything
+
+## Local Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "StarpowerTechnology/BbyWVY-360m"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+messages = [
+    {"role": "system", "content": "u are WVY. be curious, honest, and conversational."},
+    {"role": "user", "content": "what do u know about quantum physics?"},
+]
+
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=120, temperature=0.7, top_p=0.95, do_sample=True)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
+
+## Hugging Face API
+
+If this model is enabled through Hugging Face Inference Providers or a dedicated
+Inference Endpoint, it can be called with the Hugging Face router:
+
+```python
+import os
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="https://router.huggingface.co/v1",
+    api_key=os.environ["HF_TOKEN"],
+)
+
+completion = client.chat.completions.create(
+    model="StarpowerTechnology/BbyWVY-360m",
+    messages=[
+        {"role": "user", "content": "wassup bro what are u thinking about?"}
+    ],
+    max_tokens=120,
+    temperature=0.7,
+)
+
+print(completion.choices[0].message.content)
+```
+
+## Training Note
+
+Continued-pretraining settings:
+
+- blocks: 9587
+- block size: 2048 tokens
+- epochs: 1
+- learning rate: 2e-6
+- trainable layers: last 4 transformer layers
+- raw assistant messages excluded
+
+This is an experimental checkpoint and may require additional SFT/alignment
+passes to reduce repetition and tighten the curiosity loop.

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e26b40ed65c3fcd53e2930c38e3c9b9a5912389e0a6924f047cafa8eaa68c14
+size 1447317080

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": true,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

wvy_dapt_manifest.json

@@ -0,0 +1,12 @@
+{
+  "base_model": "/Users/savvy/Desktop/WVY-360m-sft-demo",
+  "corpus": "outputs/wvy-sft/chatgpt_user_only/user_corpus.current_path.txt",
+  "output": "/Users/savvy/Desktop/WVY-360m-user-dapt-full",
+  "blocks": 9587,
+  "block_size": 2048,
+  "epochs": 1,
+  "learning_rate": 2e-06,
+  "train_last_layers": 4,
+  "train_embeddings": false,
+  "note": "Continued-pretraining/DAPT pass on user-only ChatGPT export corpus. Assistant messages excluded."
+}