deepseek-llm:67b-base-q3_K_M

152.6K 1 year ago

An advanced language model crafted with 2 trillion bilingual tokens.

7b 67b

1 year ago

528e5a0d9578 · 33GB

llama
·
67.4B
·
Q3_K_M
{ "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