初始化项目，由ModelHub XC社区提供模型
Model: LLM-Research/OLMoE-1B-7B-0924-SFT 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
|
||||
43
README.md
Normal file
43
README.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- moe
|
||||
- olmo
|
||||
- olmoe
|
||||
co2_eq_emissions: 1
|
||||
datasets:
|
||||
- allenai/tulu-v3.1-mix-preview-4096-OLMoE
|
||||
base_model: allenai/OLMoE-1B-7B-0924
|
||||
---
|
||||
|
||||
<img alt="OLMoE Logo." src="olmoe-logo.png" width="250px">
|
||||
|
||||
# Model Summary
|
||||
|
||||
This model is an intermediate training checkpoint during post-training, after the Supervised Fine-Tuning (SFT) step. For best performance, we recommend you use the [OLMoE-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct) version.
|
||||
|
||||
- **Paper**: https://arxiv.org/abs/2409.02060
|
||||
- **Pretraining** [Checkpoints](https://hf.co/allenai/OLMoE-1B-7B-0924), [Code](https://github.com/allenai/OLMo/tree/Muennighoff/MoE), [Data](https://huggingface.co/datasets/allenai/OLMoE-mix-0924) and [Logs](https://wandb.ai/ai2-llm/olmoe/reports/OLMoE-1B-7B-0924--Vmlldzo4OTcyMjU3).
|
||||
- **SFT (Supervised Fine-Tuning)** [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-SFT), [Code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [Data](https://hf.co/datasets/allenai/tulu-v3.1-mix-preview-4096-OLMoE) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-sft-logs.txt).
|
||||
- **DPO/KTO (Direct Preference Optimization/Kahneman-Tversky Optimization)**, [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct), [Preference Data](https://hf.co/datasets/allenai/ultrafeedback_binarized_cleaned), [DPO code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [KTO code](https://github.com/Muennighoff/kto/blob/master/kto.py) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-dpo-logs.txt).
|
||||
|
||||
Branches:
|
||||
- `main`: Instruction tuned / supervised finetuned (SFT) model of https://hf.co/allenai/OLMoE-1B-7B-0924 (`main` branch)
|
||||
- `load-balancing`: Ablation with load balancing loss during SFT
|
||||
- `non-annealed`: Ablation starting from the checkpoint prior to annealing (branch `step1200000-tokens5033B` of https://hf.co/allenai/OLMoE-1B-7B-0924) rather than the annealed checkpoint (branch `main` of https://hf.co/allenai/OLMoE-1B-7B-0924)
|
||||
|
||||
# Citation
|
||||
|
||||
```bibtex
|
||||
@misc{muennighoff2024olmoeopenmixtureofexpertslanguage,
|
||||
title={OLMoE: Open Mixture-of-Experts Language Models},
|
||||
author={Niklas Muennighoff and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Jacob Morrison and Sewon Min and Weijia Shi and Pete Walsh and Oyvind Tafjord and Nathan Lambert and Yuling Gu and Shane Arora and Akshita Bhagia and Dustin Schwenk and David Wadden and Alexander Wettig and Binyuan Hui and Tim Dettmers and Douwe Kiela and Ali Farhadi and Noah A. Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi},
|
||||
year={2024},
|
||||
eprint={2409.02060},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2409.02060},
|
||||
}
|
||||
```
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"architectures": [
|
||||
"OlmoeForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"clip_qkv": null,
|
||||
"eos_token_id": 50279,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 1024,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "olmoe",
|
||||
"norm_topk_prob": false,
|
||||
"num_attention_heads": 16,
|
||||
"num_experts": 64,
|
||||
"num_experts_per_tok": 8,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 16,
|
||||
"output_router_logits": false,
|
||||
"pad_token_id": 1,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"router_aux_loss_coef": 0.01,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
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,
|
||||
"eos_token_id": 50279,
|
||||
"pad_token_id": 1,
|
||||
"transformers_version": "4.44.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:660f006150a625e0b2f6df2bb1344a1d33ba2185fe92dccfffbf3f7494856c6b
|
||||
size 4997744872
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5688cc530e68648e30a86f33a0a682c31e764e54b4feca21e866b9298a50e390
|
||||
size 4997235176
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed7c22a0294829f52e8a6a66571c3acaeb1cc53b0c890075622b21f43ceebe59
|
||||
size 3843741912
|
||||
3226
model.safetensors.index.json
Normal file
3226
model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
olmoe-logo.png
Normal file
BIN
olmoe-logo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 23 KiB |
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100603
tokenizer.json
Normal file
100603
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "|||IP_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": "|||EMAIL_ADDRESS|||",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50278": {
|
||||
"content": "|||PHONE_NUMBER|||",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50279": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] }}\n{% elif message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|padding|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user