language:
- 英文
license: apache-2.0
library_name: transformers
tags:
- 合并
- 合并工具包
- 懒人合并工具包
- TensorBlock
- GGUF
base_model: ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
pipeline_tag: 文本生成
model-index:
- name: Llama-3.1-8B-SuperNova-EtherealHermes
results:
- task:
type: 文本生成
name: 文本生成
dataset:
name: IFEval (零样本)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: 实例级严格准确率和提示级严格准确率
value: 73.39
name: 严格准确率
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
- task:
type: 文本生成
name: 文本生成
dataset:
name: BBH (三样本)
type: BBH
args:
num_few_shot: 3
metrics:
- type: 标准化准确率
value: 32.07
name: 标准化准确率
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
- task:
type: 文本生成
name: 文本生成
dataset:
name: 数学五级 (四样本)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: 精确匹配
value: 17.45
name: 精确匹配
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
- task:
type: 文本生成
name: 文本生成
dataset:
name: GPQA (零样本)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: 标准化准确率
value: 5.7
name: 标准化准确率
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
- task:
type: 文本生成
name: 文本生成
dataset:
name: MuSR (零样本)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: 标准化准确率
value: 11.32
name: 标准化准确率
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
- task:
type: 文本生成
name: 文本生成
dataset:
name: MMLU-PRO (五样本)
type: TIGER-Lab/MMLU-Pro
config: 主要
split: 测试
args:
num_few_shot: 5
metrics:
- type: 准确率
value: 30.5
name: 准确率
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
name: 开放大模型排行榜
ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes - GGUF
本仓库包含ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes的GGUF格式模型文件。
这些文件由TensorBlock提供的机器进行量化,兼容截至提交b4882的llama.cpp版本。
我们的项目
## 提示模板
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{系统提示}<|eot_id|><|start_header_id|>user<|end_header_id|>
{用户提示}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
模型文件规格
下载指南
命令行方式
首先安装Huggingface客户端
pip install -U "huggingface_hub[cli]"
然后下载单个模型文件到本地目录
huggingface-cli download tensorblock/Llama-3.1-8B-SuperNova-EtherealHermes-GGUF --include "Llama-3.1-8B-SuperNova-EtherealHermes-Q2_K.gguf" --local-dir 本地目录
如需批量下载符合特定模式的文件(例如*Q4_K*gguf
),可尝试:
huggingface-cli download tensorblock/Llama-3.1-8B-SuperNova-EtherealHermes-GGUF --local-dir 本地目录 --local-dir-use-symlinks False --include='*Q4_K*gguf'