初始化项目，由ModelHub XC社区提供模型
Model: TinyModels/Atom-350M Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -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
|
||||
178
README.md
Normal file
178
README.md
Normal file
@@ -0,0 +1,178 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- assistant
|
||||
- chat
|
||||
- general-purpose
|
||||
- smollm2
|
||||
- tiny
|
||||
- efficient
|
||||
- tinymodels
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
<svg width="100" height="100" viewBox="0 0 100 100" xmlns="http://www.w3.org/2000/svg" style="animation: float 4s ease-in-out infinite;">
|
||||
<circle cx="50" cy="50" r="45" fill="none" stroke="url(#grad1)" stroke-width="3"/>
|
||||
<circle cx="50" cy="50" r="30" fill="none" stroke="url(#grad2)" stroke-width="2" stroke-dasharray="8,6"/>
|
||||
<circle cx="50" cy="50" r="12" fill="url(#grad3)"/>
|
||||
<defs>
|
||||
<linearGradient id="grad1" x1="0%" y1="0%" x2="100%" y2="100%">
|
||||
<stop offset="0%" style="stop-color:#ff0080;stop-opacity:1" />
|
||||
<stop offset="100%" style="stop-color:#7928ca;stop-opacity:1" />
|
||||
</linearGradient>
|
||||
<linearGradient id="grad2" x1="100%" y1="0%" x2="0%" y2="100%">
|
||||
<stop offset="0%" style="stop-color:#7928ca;stop-opacity:1" />
|
||||
<stop offset="100%" style="stop-color:#ff0080;stop-opacity:1" />
|
||||
</linearGradient>
|
||||
<radialGradient id="grad3" cx="30%" cy="30%" r="70%">
|
||||
<stop offset="0%" style="stop-color:#ff0080;stop-opacity:1" />
|
||||
<stop offset="100%" style="stop-color:#7928ca;stop-opacity:1" />
|
||||
</radialGradient>
|
||||
</defs>
|
||||
</svg>
|
||||
</div>
|
||||
|
||||
<h1 align="center" style="font-family: 'Orbitron', sans-serif; font-size: 3rem; letter-spacing: 2px; margin-top: 10px; background: linear-gradient(135deg, #ff0080, #7928ca); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">ATOM‑350M</h1>
|
||||
<p align="center" style="font-family: 'Rajdhani', sans-serif; font-size: 1.5rem; color: #b0b0b0; margin-top: -10px;">Tiny models, <strong style="color: #ff0080;">big</strong> ideas.</p>
|
||||
|
||||
<div align="center" style="margin: 30px 0;">
|
||||
<span style="background: rgba(255,0,128,0.1); border: 1px solid rgba(255,0,128,0.3); border-radius: 50px; padding: 6px 20px; font-family: 'Rajdhani', sans-serif; font-weight: 600; font-size: 0.9rem; color: #ff0080; letter-spacing: 1px;">
|
||||
⚡ BUILT BY TINYMODELS
|
||||
</span>
|
||||
</div>
|
||||
|
||||
<p align="center" style="max-width: 700px; margin: 0 auto; font-family: 'Rajdhani', sans-serif; font-size: 1.1rem; color: #aaa; line-height: 1.6;">
|
||||
A lightning‑fast, open‑source AI assistant forged in the heart of the TinyModels community. Hand‑picked data, real‑world training, and a personality that doesn't feel like a corporate robot. This is our take on what a compact, genuinely useful model should be.
|
||||
</p>
|
||||
|
||||
<div align="center" style="margin: 40px 0;">
|
||||
<a href="#quick-start" style="background: linear-gradient(135deg, #ff0080, #7928ca); color: white; padding: 14px 36px; border-radius: 50px; font-family: 'Orbitron', sans-serif; font-weight: 600; text-decoration: none; font-size: 1rem; box-shadow: 0 4px 20px rgba(255,0,128,0.4); transition: 0.2s;">
|
||||
⬇ GET STARTED
|
||||
</a>
|
||||
</div>
|
||||
|
||||
<div style="display: flex; justify-content: center; gap: 40px; margin: 60px 0; flex-wrap: wrap;">
|
||||
<div style="text-align: center; padding: 24px; border: 1px solid rgba(255,255,255,0.08); border-radius: 20px; background: rgba(20,20,30,0.6); backdrop-filter: blur(10px); width: 160px;">
|
||||
<div style="font-family: 'Orbitron', sans-serif; font-size: 2rem; color: #ff0080;">360M</div>
|
||||
<div style="color: #888; font-family: 'Rajdhani', sans-serif;">Parameters</div>
|
||||
</div>
|
||||
<div style="text-align: center; padding: 24px; border: 1px solid rgba(255,255,255,0.08); border-radius: 20px; background: rgba(20,20,30,0.6); backdrop-filter: blur(10px); width: 160px;">
|
||||
<div style="font-family: 'Orbitron', sans-serif; font-size: 2rem; color: #7928ca;">724 MB</div>
|
||||
<div style="color: #888; font-family: 'Rajdhani', sans-serif;">Size (FP16)</div>
|
||||
</div>
|
||||
<div style="text-align: center; padding: 24px; border: 1px solid rgba(255,255,255,0.08); border-radius: 20px; background: rgba(20,20,30,0.6); backdrop-filter: blur(10px); width: 160px;">
|
||||
<div style="font-family: 'Orbitron', sans-serif; font-size: 2rem; color: #ff0080;">1 Epoch</div>
|
||||
<div style="color: #888; font-family: 'Rajdhani', sans-serif;">Focused Training</div>
|
||||
</div>
|
||||
<div style="text-align: center; padding: 24px; border: 1px solid rgba(255,255,255,0.08); border-radius: 20px; background: rgba(20,20,30,0.6); backdrop-filter: blur(10px); width: 160px;">
|
||||
<div style="font-family: 'Orbitron', sans-serif; font-size: 2rem; color: #7928ca;">Apache 2.0</div>
|
||||
<div style="color: #888; font-family: 'Rajdhani', sans-serif;">License</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
<div id="quick-start"></div>
|
||||
<h2 style="font-family: 'Orbitron', sans-serif; color: #fff; font-size: 1.8rem;">🚀 QUICK START</h2>
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"TinyModels/Atom-350M",
|
||||
torch_dtype="auto",
|
||||
device_map="auto",
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained("TinyModels/Atom-350M")
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Explain how a bicycle stays upright in simple terms."}
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
|
||||
outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7)
|
||||
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
<h2 style="font-family: 'Orbitron', sans-serif; color: #fff; font-size: 1.8rem;">🔧 OUR RECIPE</h2>
|
||||
|
||||
<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(250px, 1fr)); gap: 20px; margin: 30px 0;">
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">BASE MODEL</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">SmolLM2‑360M‑Instruct</p>
|
||||
</div>
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">FINE‑TUNING</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">QLoRA (4‑bit, rank‑16)</p>
|
||||
</div>
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">TRAINING DATA</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">SmolTalk (smol‑magpie‑ultra)</p>
|
||||
</div>
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">FRAMEWORK</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">Unsloth + Hugging Face</p>
|
||||
</div>
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">HARDWARE</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">Kaggle T4 (free tier!)</p>
|
||||
</div>
|
||||
<div style="background: rgba(20,20,30,0.7); border: 1px solid rgba(255,0,128,0.2); border-radius: 16px; padding: 20px;">
|
||||
<h3 style="font-family: 'Orbitron', sans-serif; color: #ff0080; font-size: 1rem;">EPOCHS</h3>
|
||||
<p style="color: #bbb; font-family: 'Rajdhani', sans-serif; margin: 0;">1 — lean & efficient</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
<h2 style="font-family: 'Orbitron', sans-serif; color: #fff; font-size: 1.8rem;">🤍 THIS IS OURS</h2>
|
||||
|
||||
<p style="font-family: 'Rajdhani', sans-serif; color: #bbb; font-size: 1.1rem; line-height: 1.6; max-width: 800px;">
|
||||
<strong style="color: #ff0080;">We didn't just download a model and slap a name on it.</strong> TinyModels hand‑picked the training data, configured the QLoRA adapters, and ran the entire training pipeline ourselves. Atom‑350M is <em>our</em> interpretation of a small, helpful, open assistant — built with pride, released with no strings attached.
|
||||
</p>
|
||||
|
||||
<p style="font-family: 'Rajdhani', sans-serif; color: #aaa; font-size: 1rem; margin-top: 10px;">
|
||||
If you do something cool with it, just give us a shout‑out. We'd love to see what you build.
|
||||
</p>
|
||||
|
||||
---
|
||||
|
||||
<h2 style="font-family: 'Orbitron', sans-serif; color: #fff; font-size: 1.8rem;">📜 LICENSE</h2>
|
||||
|
||||
<p style="font-family: 'Rajdhani', sans-serif; color: #bbb; font-size: 1.1rem;">
|
||||
Apache 2.0 — free for research, commercial use, and even intergalactic travel.
|
||||
</p>
|
||||
|
||||
<div align="center" style="margin: 60px 0 20px;">
|
||||
<p style="font-family: 'Rajdhani', sans-serif; color: #555; font-size: 0.9rem;">
|
||||
Crafted by <strong style="color: #ff0080;">TinyModels</strong> — small models, big ambitions.
|
||||
</p>
|
||||
</div>
|
||||
|
||||
<style>
|
||||
@import url('https://fonts.googleapis.com/css2?family=Orbitron:wght@500;600;700&family=Rajdhani:wght@400;500;600&display=swap');
|
||||
|
||||
body {
|
||||
background: #0c0c14;
|
||||
color: #ccc;
|
||||
}
|
||||
|
||||
@keyframes float {
|
||||
0% { transform: translateY(0); }
|
||||
50% { transform: translateY(-8px); }
|
||||
100% { transform: translateY(0); }
|
||||
}
|
||||
|
||||
a {
|
||||
color: #ff0080;
|
||||
text-decoration: none;
|
||||
}
|
||||
</style>
|
||||
6
chat_template.jinja
Normal file
6
chat_template.jinja
Normal file
@@ -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 %}
|
||||
40
config.json
Normal file
40
config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"torch_dtype": "float16",
|
||||
"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": 0,
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"unsloth_version": "2026.5.8",
|
||||
"use_cache": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
2
|
||||
],
|
||||
"max_length": 8192,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b17f65157e6c2a089906d2ec274a262e80a9b83e2a184de85d87897ff71faf0
|
||||
size 723674912
|
||||
BIN
tinymodels.png
Normal file
BIN
tinymodels.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 5.8 KiB |
244965
tokenizer.json
Normal file
244965
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
155
tokenizer_config.json
Normal file
155
tokenizer_config.json
Normal file
@@ -0,0 +1,155 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|im_start|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [],
|
||||
"is_local": false,
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"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 %}"
|
||||
}
|
||||
Reference in New Issue
Block a user