Commit
β’
afcb675
1
Parent(s):
db48fe4
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,13 +81,13 @@ pinned: false
|
|
| 81 |
- Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with `ChatGPT`, even with a `7B` model which can be run on a **consumer GPU (e.g. RTX 3090)**.
|
| 82 |
- Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.
|
| 83 |
|
| 84 |
-
#
|
| 85 |
|
| 86 |
- [2023/11/01] We released the [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5) model, surpassing ChatGPT on various benchmarks π₯.
|
| 87 |
|
| 88 |
- [2023/09/21] We released our paper [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://arxiv.org/pdf/2309.11235.pdf).
|
| 89 |
|
| 90 |
-
#
|
| 91 |
|
| 92 |
| Model | # Params | Average | MT-Bench | AGIEval | BBH MC | TruthfulQA | MMLU | HumanEval | BBH CoT | GSM8K |
|
| 93 |
|--------------------|----------|----------|--------------|----------|----------|---------------|--------------|-----------------|-------------|--------------|
|
|
@@ -102,7 +102,7 @@ pinned: false
|
|
| 102 |
| | | | WizardLM 70B | Orca 13B | Orca 13B | Platypus2 70B | WizardLM 70B | WizardCoder 34B | Flan-T5 11B | MetaMath 70B |
|
| 103 |
|
| 104 |
|
| 105 |
-
##
|
| 106 |
|
| 107 |
| | License | # Param | Average | MMLU | HumanEval | MATH | GSM8k |
|
| 108 |
|--------------|-------------|---------|----------|------|-----------|----------|----------|
|
|
|
|
| 81 |
- Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with `ChatGPT`, even with a `7B` model which can be run on a **consumer GPU (e.g. RTX 3090)**.
|
| 82 |
- Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.
|
| 83 |
|
| 84 |
+
# π° News
|
| 85 |
|
| 86 |
- [2023/11/01] We released the [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5) model, surpassing ChatGPT on various benchmarks π₯.
|
| 87 |
|
| 88 |
- [2023/09/21] We released our paper [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://arxiv.org/pdf/2309.11235.pdf).
|
| 89 |
|
| 90 |
+
# π Benchmarks
|
| 91 |
|
| 92 |
| Model | # Params | Average | MT-Bench | AGIEval | BBH MC | TruthfulQA | MMLU | HumanEval | BBH CoT | GSM8K |
|
| 93 |
|--------------------|----------|----------|--------------|----------|----------|---------------|--------------|-----------------|-------------|--------------|
|
|
|
|
| 102 |
| | | | WizardLM 70B | Orca 13B | Orca 13B | Platypus2 70B | WizardLM 70B | WizardCoder 34B | Flan-T5 11B | MetaMath 70B |
|
| 103 |
|
| 104 |
|
| 105 |
+
## π Comparison with [X.AI Grok](https://x.ai/)
|
| 106 |
|
| 107 |
| | License | # Param | Average | MMLU | HumanEval | MATH | GSM8k |
|
| 108 |
|--------------|-------------|---------|----------|------|-----------|----------|----------|
|