xLakeChat / README.md
fhai50032's picture
Adding Evaluation Results (#1)
71448ad verified
---
license: apache-2.0
tags:
- merge
- mergekit
- mistral
- xDAN-AI/xDAN-L1-Chat-RL-v1
- fhai50032/BeagleLake-7B-Toxic
base_model:
- xDAN-AI/xDAN-L1-Chat-RL-v1
- fhai50032/BeagleLake-7B-Toxic
model-index:
- name: xLakeChat
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: 62.37
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 82.64
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 59.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 52.96
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 74.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
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: 50.27
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/xLakeChat
name: Open LLM Leaderboard
---
# xLakeChat
xLakeChat is a merge of the following models
* [xDAN-AI/xDAN-L1-Chat-RL-v1](https://huggingface.co/xDAN-AI/xDAN-L1-Chat-RL-v1)
* [fhai50032/BeagleLake-7B-Toxic](https://huggingface.co/fhai50032/BeagleLake-7B-Toxic)
## 🧩 Configuration
```yaml
models:
- model: senseable/WestLake-7B-v2
# no params for base model
- model: xDAN-AI/xDAN-L1-Chat-RL-v1
parameters:
weight: 0.73
density: 0.64
- model: fhai50032/BeagleLake-7B-Toxic
parameters:
weight: 0.46
density: 0.55
merge_method: dare_ties
base_model: senseable/WestLake-7B-v2
parameters:
normalize: true
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "fhai50032/xLakeChat"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
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_fhai50032__xLakeChat)
| Metric |Value|
|---------------------------------|----:|
|Avg. |63.72|
|AI2 Reasoning Challenge (25-Shot)|62.37|
|HellaSwag (10-Shot) |82.64|
|MMLU (5-Shot) |59.32|
|TruthfulQA (0-shot) |52.96|
|Winogrande (5-shot) |74.74|
|GSM8k (5-shot) |50.27|