update readme

README.md

@@ -1,15 +1,68 @@
-# JetMoE-8B-chat: Efficient and High-Performance LLM
+---
+license: apache-2.0
+base_model: jetmoe/jetmoe-8b
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/airoboros-3.2
+- HuggingFaceH4/Code-Feedback
+- HuggingFaceH4/orca-math-word-problems-200k
+- HuggingFaceH4/SystemChat
+- HuggingFaceH4/capybara
+model-index:
+- name: jetmoe-8b-sft
+  results: []
+---
 
-Welcome to the official repository of JetMoE-8B-chat, a language model that combines cost-efficiency with high performance, making state-of-the-art language modeling accessible to a broader audience, including academia and small-scale industry players.
+<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>
 
-## Key Highlights
+# JetMoE: Reaching LLaMA2 Performance with 0.1M Dollars
 
-- **Cost-Effective Training**: Achieved at less than $0.1 million, JetMoE-8B significantly lowers the barrier to entry for training large language models (LLMs), demonstrating that high-quality LLM training can be far more economical than widely assumed.
-- **Academia-Friendly**: By relying exclusively on public datasets and open-sourcing our code, JetMoE-8B is highly accessible for educational and research purposes. It is designed to be fine-tuned even on consumer-grade GPUs, making it feasible for most academic labs.
-- **Efficiency at Scale**: With only 2.2B active parameters during inference, JetMoE-8B provides an optimal balance between computational cost and performance, outperforming similarly sized models such as Gemma-2B across various benchmarks.
-- **Good Performence** JetMoE-8B-chat has been evaluated using the MT-Bench, surpassing Llama-2-13b-chat and  Vicuna-13b-v1.3. Here is how JetMoE-8B-chat compares with other models:
+## Key Messages
 
-| Model               | Score     |
+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**.
+
+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.
+
+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.
+
+<sup>1</sup> We used a 96×H100 GPU cluster for 2 weeks, which cost ~$0.08 million.
+
+Website: [https://research.myshell.ai/jetmoe](https://research.myshell.ai/jetmoe)
+
+HuggingFace: [https://huggingface.co/jetmoe/jetmoe-8b](https://huggingface.co/jetmoe/jetmoe-8b)
+
+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)
+
+## Authors
+
+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/).
+
+## 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.
+
+## 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|
+
+| Model               | MT-Bench Score     |
 |---------------------|-----------|
 | GPT-4               | 9.014     |
 | GPT-3.5-turbo       | 7.995     |
@@ -21,9 +74,10 @@ Welcome to the official repository of JetMoE-8B-chat, a language model that comb
 | Llama-2-7b-chat     | 6.269     |
 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/638e4e66629b4d0a62ce1bf3/VU0f0E-CKmMHs-PVE-8dZ.png)
 
-### Usage
+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
 
 Here's a quick example to get you started with JetMoE-8B-chat:
 
@@ -61,4 +115,41 @@ if torch.cuda.is_available():
 # Decode the generated text
 generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 print(generated_text)
-```
+```
+
+## 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.

config.json

@@ -1,92 +1,30 @@
 {
-  "_attn_implementation_internal": "eager",
-  "_commit_hash": "e4d9ef770a272f072cac70d16dd1ae113f5989ae",
   "_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
+}