update model config and readme

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 base_model: jetmoe/jetmoe-8b
 tags:
 - alignment-handbook
@@ -15,58 +16,118 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+<div align="center">
+  <div>&nbsp;</div>
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/641de0213239b631552713e4/ieHnwuczidNNoGRA_FN2y.png" width="500"/> 
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/641de0213239b631552713e4/UOsk9_zcbHpCCy6kmryYM.png" width="530"/> 
+</div>
 
-# jetmoe-8b-sft
+# JetMoE: Reaching LLaMA2 Performance with 0.1M Dollars
 
-This model is a fine-tuned version of [jetmoe-8b](https://huggingface.co/jetmoe/jetmoe-8b) on the HuggingFaceH4/ultrachat_200k, the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets.
-It achieves the following results on the evaluation set:
-- Loss: 0.9952
+## Key Messages
 
-## Model description
+1. JetMoE-8B is **trained with less than $ 0.1 million**<sup>1</sup> **cost but outperforms LLaMA2-7B from Meta AI**, who has multi-billion-dollar training resources. LLM training can be **much cheaper than people previously thought**.
 
-More information needed
+2. JetMoE-8B is **fully open-sourced and academia-friendly** because:
+    - It **only uses public datasets** for training, and the code is open-sourced. No proprietary resource is needed.
+    - It **can be finetuned with very limited compute budget** (e.g., consumer-grade GPU) that most labs can afford.
 
-## Intended uses & limitations
+3. JetMoE-8B **only has 2.2B active parameters** during inference, which drastically lowers the computational cost. Compared to a model with similar inference computation, like Gemma-2B, JetMoE-8B achieves constantly better performance.
 
-More information needed
+<sup>1</sup> We used a 96×H100 GPU cluster for 2 weeks, which cost ~$0.08 million.
 
-## Training and evaluation data
+Website: [https://research.myshell.ai/jetmoe](https://research.myshell.ai/jetmoe)
 
-More information needed
+HuggingFace: [https://huggingface.co/jetmoe/jetmoe-8b](https://huggingface.co/jetmoe/jetmoe-8b)
 
-## Training procedure
+Online Demo on Lepton AI: [https://www.lepton.ai/playground/chat?model=jetmoe-8b-chat](https://www.lepton.ai/playground/chat?model=jetmoe-8b-chat)
 
-### Training hyperparameters
+## Authors
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
-- total_eval_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+The project is contributed by [Yikang Shen](https://scholar.google.com.hk/citations?user=qff5rRYAAAAJ), [Zhen Guo](https://zguo0525.github.io/), [Tianle Cai](https://www.tianle.website/#/) and [Zengyi Qin](https://www.qinzy.tech/). For technical inquiries, please contact [Yikang Shen](https://scholar.google.com.hk/citations?user=qff5rRYAAAAJ). For media and collaboration inquiries, please contact [Zengyi Qin](https://www.qinzy.tech/).
 
-### Training results
+## Collaboration
+**If you have great ideas but need more resources (GPU, data, funding, etc.)**, welcome to contact **MyShell.ai** via [Zengyi Qin](https://www.qinzy.tech/). **MyShell.ai** is open to collaborations and are actively supporting high-quality open-source projects.
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.2458        | 1.0   | 2049 | 0.9776          |
-| 1.1966        | 2.0   | 4099 | 0.9756          |
-| 1.1073        | 3.0   | 6147 | 0.9952          |
+## Benchmarks
+We use the same evaluation methodology as in the Open LLM leaderboard. For MBPP code benchmark, we use the same evaluation methodology as in the LLaMA2 and Deepseek-MoE paper. The results are shown below:
 
+|Model|Activate Params|Training Tokens|Open LLM Leaderboard Avg|ARC|Hellaswag|MMLU|TruthfulQA|WinoGrande|GSM8k|MBPP|HumanEval|
+|---|---|---|---|---|---|---|---|---|---|---|---|
+|Shot||||25|10|5|0|5|5|3|0|
+|Metric||||acc_norm|acc_norm|acc|mc2|acc|acc|Pass@1|Pass@1|
+|LLaMA2-7B|7B|2T|51.0|53.1|78.6|46.9|38.8|74|14.5|20.8|12.8|
+|LLaMA-13B|13B|1T|51.4|**56.2**|**80.9**|47.7|39.5|**76.2**|7.6|22.0|15.8|
+|DeepseekMoE-16B|2.8B|2T|51.1|53.2|79.8|46.3|36.1|73.7|17.3|34.0|**25.0**|
+|Gemma-2B|2B|2T|46.4|48.4|71.8|41.8|33.1|66.3|16.9|28.0|24.4|
+|JetMoE-8B|2.2B|1.25T|**53.0**|48.7|80.5|**49.2**|**41.7**|70.2|**27.8**|**34.2**|14.6|
 
-### Framework versions
+| Model               | MT-Bench Score     |
+|---------------------|-----------|
+| GPT-4               | 9.014     |
+| GPT-3.5-turbo       | 7.995     |
+| Claude-v1           | 7.923     |
+| **JetMoE-8B-chat**  | **6.681** |
+| Llama-2-13b-chat    | 6.650     |
+| Vicuna-13b-v1.3     | 6.413     |
+| Wizardlm-13b        | 6.353     |
+| Llama-2-7b-chat     | 6.269     |
+
+To our surprise, despite the lower training cost and computation, JetMoE-8B performs even better than LLaMA2-7B, LLaMA-13B, and DeepseekMoE-16B. Compared to a model with similar training and inference computation, like Gemma-2B, JetMoE-8B achieves better performance.
+
+## Model Usage
+To load the models, you need install [this package](https://github.com/myshell-ai/JetMoE):
+```
+pip install -e .
+```
+
+Then you can load the model with the following code:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig, AutoModelForSequenceClassification
+from jetmoe import JetMoEForCausalLM, JetMoEConfig, JetMoEForSequenceClassification
+
+AutoConfig.register("jetmoe", JetMoEConfig)
+AutoModelForCausalLM.register(JetMoEConfig, JetMoEForCausalLM)
+AutoModelForSequenceClassification.register(JetMoEConfig, JetMoEForSequenceClassification)
+
+tokenizer = AutoTokenizer.from_pretrained('jetmoe/jetmoe-8b')
+model = AutoModelForCausalLM.from_pretrained('jetmoe/jetmoe-8b')
+```
+
+## Model Details
+JetMoE-8B has 24 blocks. 
+Each block has two MoE layers: Mixture of Attention heads (MoA) and Mixture of MLP Experts (MoE).
+Each MoA and MoE layer has 8 expert, and 2 experts are activated for each input token.
+It has 8 billion parameters in total and 2.2B active parameters. 
+JetMoE-8B is trained on 1.25T tokens from publicly available datasets, with a learning rate of 5.0 x 10<sup>-4</sup> and a global batch-size of 4M tokens.
+
+<figure>
+<center>
+<img src="images/jetmoe_architecture.png" width="40%">
+<figcaption>JetMoE Architecture</figcaption>
+</center>
+</figure>
+
+## Training Details
+Our training recipe follows the [MiniCPM](https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4)'s two-phases training method. Phase 1 uses a constant learning rate with linear warmup and is trained on 1 trillion tokens from large-scale open-source pretraining datasets, including RefinedWeb, Pile, Github data, etc. Phase 2 uses exponential learning rate decay and is trained on 250 billion tokens from phase 1 datasets and extra high-quality open-source datasets.
+
+<figure>
+<center>
+<img src="images/Phase1_data.png" width="60%">
+<img src="images/Phase2_data.png" width="60%">
+</center>
+</figure>
+
+## Technical Report
+For more details, please refer to the JetMoE Technical Report (Coming Soon).
+
+## JetMoE Model Index
+|Model|Index|
+|---|---|
+|JetMoE-8B-Base| [Link](https://huggingface.co/jetmoe/jetmoe-8B) |
+|JetMoE-8B-SFT| [Link](https://huggingface.co/jetmoe/jetmoe-8B-sft) |
+|JetMoE-8B-Chat| [Link](https://huggingface.co/jetmoe/jetmoe-8B-chat) |
+
+## Acknowledgement
+We express our gratitude to [Shengding Hu](https://shengdinghu.github.io/) for his valuable advice on the Phase 2 data mixture. We also express our gratitude to [Exabits](https://www.exabits.ai/) for their assistance in setting up the GPU clusters, and to [Lepton AI](https://www.lepton.ai/) for their support in setting up the chat demo.
 
-- Transformers 4.39.0.dev0
-- Pytorch 2.1.2
-- Datasets 2.14.6
-- Tokenizers 0.15.2

config.json

@@ -1,92 +1,30 @@
 {
-  "_attn_implementation_internal": "flash_attention_2",
-  "_commit_hash": null,
-  "_name_or_path": "jetmoe/jetmoe-8b-sft",
+  "_name_or_path": "jetmoe/jetmoe-8b-chat",
+  "model_type": "jetmoe",
   "activation_function": "silu",
-  "add_cross_attention": false,
   "architectures": [
     "JetMoEForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_jetmoe.JetMoEConfig",
-    "AutoModelForCausalLM": "modeling_jetmoe.JetMoEForCausalLM"
-  },
-  "aux_loss_coef": 0.01,
-  "bad_words_ids": null,
-  "begin_suppress_tokens": null,
-  "bias": true,
   "bos_token_id": 1,
-  "chunk_size_feed_forward": 0,
-  "cross_attention_hidden_size": null,
-  "decoder_start_token_id": null,
-  "diversity_penalty": 0.0,
-  "do_sample": false,
-  "early_stopping": false,
-  "encoder_no_repeat_ngram_size": 0,
   "eos_token_id": 2,
-  "exponential_decay_length_penalty": null,
   "ffn_hidden_size": 5632,
-  "finetuning_task": null,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "glu": true,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "initializer_range": 0.01,
-  "is_decoder": false,
-  "is_encoder_decoder": false,
   "kv_channels": 128,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
   "layer_norm_epsilon": 1e-05,
   "length_penalty": 1.0,
-  "max_length": 20,
-  "min_length": 0,
-  "model_type": "jetmoe",
   "moe_num_experts": 8,
   "moe_top_k": 2,
-  "n_embd": 2048,
-  "n_head": 16,
-  "n_layer": 24,
+  "hidden_size": 2048,
+  "num_hidden_layers": 24,
   "n_positions": 4096,
-  "no_repeat_ngram_size": 0,
-  "num_beam_groups": 1,
-  "num_beams": 1,
+  "num_attention_heads": 32,
   "num_key_value_heads": 16,
   "num_layers": 24,
-  "num_return_sequences": 1,
-  "output_attentions": false,
-  "output_hidden_states": false,
-  "output_scores": false,
-  "pad_token_id": null,
-  "prefix": null,
-  "problem_type": null,
-  "pruned_heads": {},
-  "remove_invalid_values": false,
-  "repetition_penalty": 1.0,
-  "return_dict": true,
-  "return_dict_in_generate": false,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "rotary_percent": 1.0,
-  "sep_token_id": null,
-  "suppress_tokens": null,
-  "task_specific_params": null,
-  "temperature": 1.0,
-  "tf_legacy_loss": false,
-  "tie_encoder_decoder": false,
   "tie_word_embeddings": true,
-  "tokenizer_class": null,
-  "top_k": 50,
-  "top_p": 1.0,
-  "torchscript": false,
   "transformers_version": null,
-  "typical_p": 1.0,
-  "use_bfloat16": false,
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32000,
+  "glu": true
 }