language:
- en
license: apache-2.0
library_name: transformers
tags:
- chat
- abliterated
- uncensored
base_model:
- huihui-ai/QwQ-32B-Preview-abliterated
- huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
license_link: https://huggingface.co/huihui-ai/QwQ-32B-Coder-Fusion-9010/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
- name: QwQ-32B-Coder-Fusion-9010
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 57.78
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 53.02
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 40.26
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 14.88
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 19.52
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 51.11
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=huihui-ai/QwQ-32B-Coder-Fusion-9010
name: Open LLM Leaderboard
huihui-ai/QwQ-32B-Coder-Fusion-9010
Overview
QwQ-32B-Coder-Fusion-9010 is a mixed model that combines the strengths of two powerful Qwen-based models: huihui-ai/QwQ-32B-Preview-abliterated and
huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.
The weights are blended in a 9:1 ratio, with 90% of the weights from the abliterated QwQ-32B-Preview-abliterated and 10% from the abliterated Qwen2.5-Coder-32B-Instruct-abliterated model.
Although it's a simple mix, the model is usable, and no gibberish has appeared.
This is an experiment. I test the 9:1,
8:2,
and 7:3 ratios separately to see how much impact they have on the model.
Now the effective ratios are 9:1, 8:2, and 7:3. Any other ratios (6:4,5:5) would result in mixed or unclear expressions.
Model Details
- Base Models:
- Model Size: 32B parameters
- Architecture: Qwen 2.5
- Mixing Ratio: 9:1 (QwQ-32B-Preview-abliterated:Qwen2.5-Coder-32B-Instruct-abliterated)
ollama
You can use huihui_ai/qwq-fusion directly,
ollama run huihui_ai/qwq-fusion
Other proportions can be obtained by visiting huihui_ai/qwq-fusion.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 39.43 |
| IFEval (0-Shot) | 57.78 |
| BBH (3-Shot) | 53.02 |
| MATH Lvl 5 (4-Shot) | 40.26 |
| GPQA (0-shot) | 14.88 |
| MuSR (0-shot) | 19.52 |
| MMLU-PRO (5-shot) | 51.11 |