HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Yi-34B-Chat-AWQ

TheBloke/Yi-34B-Chat-AWQ

kind
awq
quant
awq
family
yi
modality
text-generation
root model
01-ai/Yi-34B-Chat
provider
TheBloke
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
52
likes
14
created
—
last modified
2023-11-23T19:22:14+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Yi-34B-Chat-AWQ
tags
transformerssafetensorsllamatext-generationconversationalbase_model:01-ai/Yi-34B-Chatbase_model:quantized:01-ai/Yi-34B-Chatlicense:othertext-generation-inference4-bitawqregion:us

Benchmark scores (7)

benchmarkcategoryscorecontextconfevidence
CMMLUknowledge79.11high| Yi-34B-Chat | **67.62** | 73.46 | **79.11** | **81.34** | 77.04 | 78.53 | 62.43 | 51.41 | **71.74** | **71.65** | **75.97** |
C-Evalknowledge77.04high| Yi-34B-Chat | **67.62** | 73.46 | **79.11** | **81.34** | 77.04 | 78.53 | 62.43 | 51.41 | **71.74** | **71.65** | **75.97** |
GSM8Kmath71.65high| Yi-34B-Chat | **67.62** | 73.46 | **79.11** | **81.34** | 77.04 | 78.53 | 62.43 | 51.41 | **71.74** | **71.65** | **75.97** |
MMLUknowledge67.62high| Yi-34B-Chat | **67.62** | 73.46 | **79.11** | **81.34** | 77.04 | 78.53 | 62.43 | 51.41 | **71.74** | **71.65** | **75.97** |
BBHreasoning51.41high| Yi-34B-Chat | **67.62** | 73.46 | **79.11** | **81.34** | 77.04 | 78.53 | 62.43 | 51.41 | **71.74** | **71.65** | **75.97** |
GAOKAOknowledge49.8low| LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 |
MATHmath26.0low| LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.