Commit History

Author SHA1 Message Date
  AlpinDale 5a74656527 API key for ooba server 1 year ago
  AlpinDale dce63739d0 remove unnecessary api server 1 year ago
  AlpinDale ac61b31879 fix top_k in server 1 year ago
  AlpinDale 9e52536059 fix ooba server 1 year ago
  AlpinDale 31c6dfb2ee fix api again 1 year ago
  AlpinDale 95552bfb38 fix model api 1 year ago
  AlpinDale 58c11e2178 remove revision from the loader 1 year ago
  AlpinDale 22fe51d5c3 remove revision from llama for now 1 year ago
  AlpinDale 96c6d2065d test api server 1 year ago
  AlpinDale 9328091450 Revert a revert. 1 year ago
  AlpinDale 39beed0b87 Revert "Refactor AWQ support." 1 year ago
  AlpinDale 579071b570 Revert "fix the awq gemm kernels" 1 year ago
  AlpinDale 663dd09399 Revert "fix: detokenization with special tokens" 1 year ago
  AlpinDale 20c27863c1 fix the awq gemm kernels 1 year ago
  AlpinDale d09e27f5d4 Refactor AWQ support. 1 year ago
  AlpinDale cc1d5339dd fix: detokenization with special tokens 1 year ago
  AlpinDale 6dfca14e1f compute logprobs with log_softmax instead of log 1 year ago
  AlpinDale 6b9561ef07 adapt TGI incremental detokenization 1 year ago
  AlpinDale d4cd18bd94 chore: allow user to specify model context length 1 year ago
  AlpinDale 0115e55972 chore: add max log length 1 year ago
  AlpinDale e77960c57e use float datatype for RoPE 1 year ago
  AlpinDale 57b5ef31e7 fix: wrong dtype in bias 1 year ago
  AlpinDale d71a84b780 fix: ModuleNotFoundError for remote code models 1 year ago
  AlpinDale 2399cbd3e6 feat: bump up the version to 0.2.1 1 year ago
  AlpinDale d949dd306f add api changes 1 year ago
  AlpinDale 7a85354b69 add logits back 1 year ago
  AlpinDale 15a4071e77 Merge pull request #12 from PygmalionAI/feat/refactor 1 year ago
  AlpinDale 45f6d9f923 initial refactor commit 1 year ago
  AlpinDale 23389d0108 zero out a variable instead of vector in kernels 1 year ago
  AlpinDale bdf264880f clean up safetensors support 1 year ago