217 lines
7.0 KiB
Markdown
217 lines
7.0 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
library_name: transformers
|
|
tags:
|
|
- merge
|
|
base_model:
|
|
- sethuiyer/SynthIQ-7b
|
|
- openchat/openchat-3.5-0106
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: Chikuma_10.7B
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: AI2 Reasoning Challenge (25-Shot)
|
|
type: ai2_arc
|
|
config: ARC-Challenge
|
|
split: test
|
|
args:
|
|
num_few_shot: 25
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 65.7
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: HellaSwag (10-Shot)
|
|
type: hellaswag
|
|
split: validation
|
|
args:
|
|
num_few_shot: 10
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 84.31
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MMLU (5-Shot)
|
|
type: cais/mmlu
|
|
config: all
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 64.81
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: TruthfulQA (0-shot)
|
|
type: truthful_qa
|
|
config: multiple_choice
|
|
split: validation
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: mc2
|
|
value: 57.01
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: Winogrande (5-shot)
|
|
type: winogrande
|
|
config: winogrande_xl
|
|
split: validation
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 79.56
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GSM8k (5-shot)
|
|
type: gsm8k
|
|
config: main
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 57.62
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Chikuma_10.7B
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
## NOTE: For experimental purposes
|
|
|
|
<p align="center">
|
|
<img src="https://huggingface.co/sethuiyer/Chikuma/resolve/main/chikuma.webp" height="256px" alt="Chikuma">
|
|
</p>
|
|
|
|
|
|
Chikuma is a 10.7B parameter model and is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
|
* [sethuiyer/SynthIQ-7b](https://huggingface.co/sethuiyer/SynthIQ-7b)
|
|
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
|
|
|
The name "Chikuma" is inspired by the [Chikuma River](https://en.wikipedia.org/wiki/Shinano_River), the longest in Japan, known for its continuous flow and meandering path.
|
|
This metaphorically represents the model's depth, fluidity, and adaptability in processing and understanding language.
|
|
|
|
It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.
|
|
|
|
## Nous LLM Evaluation (with ChatML Prompt Template)
|
|
| Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
|
|
|---------------------------|---------|----------|------------|-----------|---------|
|
|
| SynthIQ-7b | 42.67 | 73.71 | 56.51 | **44.59** | **54.37** |
|
|
| openchat/openchat-3.5-0106 | **44.17** | **73.72** | 52.53 | 44.4 | 53.71 |
|
|
| Chikuma_10.7B | 42.41 | 73.41 | **56.69** | 43.5 | 54 |
|
|
|
|
More details can be found [here](https://gist.github.com/sethuiyer/08b4498ed13a6dead38ad3a6f12e349a)
|
|
|
|
|
|
### Recommended Prompt Template (Experimental)
|
|
|
|
```text
|
|
<|im_start|>GPT4 Correct system
|
|
You are Chikuma, a constantly learning AI assistant who strives to be
|
|
insightful, engaging, and helpful. You possess vast knowledge and creativity,
|
|
but also a humble curiosity about the world and the people you interact
|
|
with. If you don't know the answer to a question, please don't share false information.
|
|
Always use <|end_of_turn|> when you want to end the answer.<|im_end|>
|
|
<|im_start|>GPT4 Correct User:
|
|
{{Input}}
|
|
<|im_end|>GPT4 Correct Assistant:
|
|
```
|
|
|
|
ChatML also works, but make sure to add the sentence "Always use <|end_of_turn|> when you want to end the answer" as the default eos token is <|end_of_turn|>.
|
|
|
|
## Tested to work well in :
|
|
1. [text-generation-webui](https://github.com/oobabooga/text-generation-webui), LLaMa-Precise sampling settings.
|
|
2. `transformers` text generation pipeline, temperature=4.0, top_k=50, top_p=0.01.
|
|
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
slices:
|
|
- sources:
|
|
- model: sethuiyer/SynthIQ-7b
|
|
layer_range: [0, 24]
|
|
- sources:
|
|
- model: openchat/openchat-3.5-0106
|
|
layer_range: [8, 32]
|
|
merge_method: passthrough
|
|
dtype: bfloat16
|
|
```
|
|
|
|
## Ollama:
|
|
Chikuma is on Ollama. You can use it by running the command ```ollama run stuehieyr/chikuma``` in your
|
|
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
|
a Google Colab backend.
|
|
|
|
## 💻 Usage
|
|
|
|
```python
|
|
sys_message = '''
|
|
You are Chikuma, a constantly learning AI assistant who strives to be
|
|
insightful, engaging, and helpful. You possess vast knowledge and creativity,
|
|
but also a humble curiosity about the world and the people you interact
|
|
with. If you don't know the answer to a question, please don't share false information.
|
|
Always use <|end_of_turn|> when you want to end the answer.
|
|
'''
|
|
|
|
question = '''
|
|
Tell me what is a large language model in under 250 words.
|
|
'''
|
|
|
|
messages = [{"role":"system", "content": sys_message}, {"role": "user", "content": question}]
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=4.0, top_k=50, top_p=0.01)
|
|
print(outputs[0]["generated_text"])
|
|
```
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__Chikuma_10.7B)
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |68.17|
|
|
|AI2 Reasoning Challenge (25-Shot)|65.70|
|
|
|HellaSwag (10-Shot) |84.31|
|
|
|MMLU (5-Shot) |64.81|
|
|
|TruthfulQA (0-shot) |57.01|
|
|
|Winogrande (5-shot) |79.56|
|
|
|GSM8k (5-shot) |57.62|
|
|
|