初始化项目，由ModelHub XC社区提供模型
Model: HuggingFaceTB/SmolLM-360M Source: Original Platform
This commit is contained in:
ModelHub XC
43
.gitattributes
vendored
Normal file
43
.gitattributes
vendored
Normal file
@@ -0,0 +1,43 @@
|
||||
*.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
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_bnb4.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_int8.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_q4.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
onnx/model_uint8.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
127
README.md
Normal file
127
README.md
Normal file
@@ -0,0 +1,127 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
datasets:
|
||||
- HuggingFaceTB/smollm-corpus
|
||||
---
|
||||
|
||||
|
||||
# SmolLM
|
||||
|
||||
<center>
|
||||
<img src="https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png" alt="SmolLM" width="1100" height="600">
|
||||
</center>
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Model Summary](##model-summary)
|
||||
2. [Limitations](##limitations)
|
||||
3. [Training](##training)
|
||||
4. [License](##license)
|
||||
5. [Citation](##citation)
|
||||
|
||||
## Model Summary
|
||||
|
||||
SmolLM is a series of state-of-the-art small language models available in three sizes: 135M, 360M, and 1.7B parameters. These models are built on Cosmo-Corpus, a meticulously curated high-quality training dataset. Cosmo-Corpus includes Cosmopedia v2 (28B tokens of synthetic textbooks and stories generated by Mixtral), Python-Edu (4B tokens of educational Python samples from The Stack), and FineWeb-Edu (220B tokens of deduplicated educational web samples from FineWeb). SmolLM models have shown promising results when compared to other models in their size categories across various benchmarks testing common sense reasoning and world knowledge. For detailed information on training, benchmarks and performance, please refer to our full [blog post](https://huggingface.co/blog/smollm).
|
||||
|
||||
This is the SmolLM-360M
|
||||
|
||||
### Generation
|
||||
```bash
|
||||
pip install transformers
|
||||
```
|
||||
|
||||
#### Running the model on CPU/GPU/multi GPU
|
||||
* _Using full precision_
|
||||
```python
|
||||
# pip install transformers
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
checkpoint = "HuggingFaceTB/SmolLM-360M"
|
||||
device = "cuda" # for GPU usage or "cpu" for CPU usage
|
||||
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
||||
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
|
||||
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
|
||||
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
|
||||
outputs = model.generate(inputs)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
|
||||
* _Using `torch.bfloat16`_
|
||||
```python
|
||||
# pip install accelerate
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
checkpoint = "HuggingFaceTB/SmolLM-360M"
|
||||
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
||||
# for fp16 use `torch_dtype=torch.float16` instead
|
||||
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)
|
||||
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to("cuda")
|
||||
outputs = model.generate(inputs)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
```bash
|
||||
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
|
||||
Memory footprint: 723.56 MB
|
||||
```
|
||||
|
||||
#### Quantized Versions through `bitsandbytes`
|
||||
* _Using 8-bit precision (int8)_
|
||||
|
||||
```python
|
||||
# pip install bitsandbytes accelerate
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
||||
# to use 4bit use `load_in_4bit=True` instead
|
||||
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
||||
checkpoint = "HuggingFaceTB/SmolLM-360M"
|
||||
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
||||
model = AutoModelForCausalLM.from_pretrained(checkpoint, quantization_config=quantization_config)
|
||||
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to("cuda")
|
||||
outputs = model.generate(inputs)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
```bash
|
||||
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
|
||||
# load_in_8bit
|
||||
Memory footprint: 409.07 MB
|
||||
# load_in_4bit
|
||||
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
|
||||
Memory footprint: 251.79 MB
|
||||
```
|
||||
|
||||
# Limitations
|
||||
|
||||
While SmolLM models have been trained on a diverse dataset including educational content and synthetic texts, they have limitations. The models primarily understand and generate content in English. They can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content. For a more comprehensive discussion of the models' capabilities and limitations, please refer to our full [blog post](https://huggingface.co/blog/smollm)..
|
||||
|
||||
This repository contains a converted version of our latest trained model. We've noticed a small performance difference between this converted checkpoint (transformers) and the original (nanotron). We're currently working to resolve this issue.
|
||||
# Training
|
||||
|
||||
## Model
|
||||
|
||||
- **Architecture:** For architecture detail, see the [blog post](https://huggingface.co/blog/smollm).
|
||||
- **Pretraining steps:** 600k
|
||||
- **Pretraining tokens:** 600B
|
||||
- **Precision:** bfloat16
|
||||
- **Tokenizer:** [HuggingFaceTB/cosmo2-tokenizer](https://huggingface.co/HuggingFaceTB/cosmo2-tokenizer)
|
||||
|
||||
|
||||
## Hardware
|
||||
|
||||
- **GPUs:** 64 H100
|
||||
|
||||
## Software
|
||||
|
||||
- **Training Framework:** [Nanotron](https://github.com/huggingface/nanotron/tree/main)
|
||||
|
||||
# License
|
||||
|
||||
[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
||||
|
||||
# Citation
|
||||
```bash
|
||||
@misc{allal2024SmolLM,
|
||||
title={SmolLM - blazingly fast and remarkably powerful},
|
||||
author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Leandro von Werra and Thomas Wolf},
|
||||
year={2024},
|
||||
}
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/fsx/elie_bakouch/checkpoints/final-362M/600000",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 960,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2560,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 15,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 5,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.41.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.41.2"
|
||||
}
|
||||
48901
merges.txt
Normal file
48901
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e91f05d8506ee5efbd8c0fbfc1799c49af2b2f2cce824bc2d801d5af2a716cc2
|
||||
size 1447317080
|
||||
3
onnx/model.onnx
Normal file
3
onnx/model.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f6f1f35ffad3f46f1bc643f428d9406c940b6f0228e5161b096eabd486ebd6f1
|
||||
size 1448301209
|
||||
3
onnx/model_bnb4.onnx
Normal file
3
onnx/model_bnb4.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3fe6f80fdd69e731caff803c9b5e5b7481b87002d52ce0fe72ba8c7d1196389
|
||||
size 366992362
|
||||
3
onnx/model_fp16.onnx
Normal file
3
onnx/model_fp16.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ed8065d648e798752e6a3fb4fb3cea97b3bddee17462e1c8c2456c74d678cb6
|
||||
size 724701643
|
||||
3
onnx/model_int8.onnx
Normal file
3
onnx/model_int8.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0441b9ae5482fdd0f1998763a28fa24f3946dfca37ef5db2e47a7a16955e508c
|
||||
size 363270670
|
||||
3
onnx/model_q4.onnx
Normal file
3
onnx/model_q4.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5a01e9e92df5c2d1e8ae297bdbcc0a648ca69774b8fa2f5ec8d7cb8c805a08ba
|
||||
size 386651434
|
||||
3
onnx/model_quantized.onnx
Normal file
3
onnx/model_quantized.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0441b9ae5482fdd0f1998763a28fa24f3946dfca37ef5db2e47a7a16955e508c
|
||||
size 363270670
|
||||
3
onnx/model_uint8.onnx
Normal file
3
onnx/model_uint8.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1093c22f701af8728c46bc83a660cd234edcc23c28edd329a00b63efffde12a4
|
||||
size 363270784
|
||||
42
special_tokens_map.json
Normal file
42
special_tokens_map.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
98249
tokenizer.json
Normal file
98249
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
167
tokenizer_config.json
Normal file
167
tokenizer_config.json
Normal file
@@ -0,0 +1,167 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user