deepseek-llm:7b-base-q6_K

148.2K 1 year ago

An advanced language model crafted with 2 trillion bilingual tokens.

7b 67b

1 year ago

5aa79848f58a · 5.7GB

llama
·
6.91B
·
Q6_K
{ "num_ctx": 4096 }

Readme

DeepSeek LLM is an advanced language model available in both 7 billion and 67 billion parameters. Both a chat and base variation are available.

  • Superior General Capabilities: DeepSeek LLM 67B Base outperforms Llama2 70B Base in areas such as reasoning, coding, math, and Chinese comprehension.

  • Proficient in Coding and Math: DeepSeek LLM 67B Chat exhibits outstanding performance in coding (using the HumanEval benchmark) and mathematics (using the GSM8K benchmark).

References

GitHub

HuggingFace