Commits

Breadcrumbs

History for

on87038fe

User selector

All users

Datepicker

All time

Commit History

Commits on Feb 21, 2024

• llama : add gemma model (#5631)

  Show description for 580111d
  postmasters

  authored
  580111d

  Copy full SHA for 580111d

Commits on Feb 15, 2024

• Use correct type of pooling for embedding models (#5500)

  Show description for 4524290
  iamlemec

  authored
  4524290

  Copy full SHA for 4524290

• fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)

  Show description for 7312247
  vriesdemichael

  authored
  7312247

  Copy full SHA for 7312247

Commits on Feb 13, 2024

• gguf : add python reader example (#5216)

  Show description for 6c00a06
  cmp-nct

  authored
  6c00a06

  Copy full SHA for 6c00a06

• llama : add support for Nomic Embed (#5468)

  cebtenzzre

  authored
  ea9c8e1

  Copy full SHA for ea9c8e1

• llama : support batched embeddings (#5466)

  Show description for 03bf161
  

  iamlemec

  and

  ggerganov

  authored
  03bf161

  Copy full SHA for 03bf161

Commits on Feb 11, 2024

• Add support for BERT embedding models (#5423)

  Show description for 2891c8a
  

  3 peopleauthored
  2891c8a

  Copy full SHA for 2891c8a

Commits on Feb 7, 2024

• llama : add MiniCPM support (#5346)

  Show description for 316c7fa
  runfuture

  authored
  316c7fa

  Copy full SHA for 316c7fa

Commits on Feb 1, 2024

• llama : support InternLM2 (#5184)

  Show description for ce32060
  SolenoidWGT

  authored
  ce32060

  Copy full SHA for ce32060

Commits on Jan 28, 2024

• llama : add support for Orion-14B (#5118)

  Show description for f2e69d2
  

  4 peopleauthored
  f2e69d2

  Copy full SHA for f2e69d2

Commits on Jan 26, 2024

• gguf : fix "general.alignment" type in gguf_reader.py (#5136)

  snowyu

  authored
  38b431d

  Copy full SHA for 38b431d

Commits on Jan 19, 2024

• llama : support upcoming Qwen2 (#5037)

  simonJJJ

  authored
  9b75cb2

  Copy full SHA for 9b75cb2

• llama : add CodeShell support (#5016)

  Show description for 2b3b999
  

  chiranko

  and

  ggerganov

  authored
  2b3b999

  Copy full SHA for 2b3b999

Commits on Jan 13, 2024

• convert : update phi-2 to latest HF repo (#4903)

  Show description for 15ebe59
  ggerganov

  authored
  15ebe59

  Copy full SHA for 15ebe59

Commits on Jan 12, 2024

• llama : fix llm_build_k_shift to use correct n_rot (#4889)

  Show description for f445c0e
  ggerganov

  authored
  f445c0e

  Copy full SHA for f445c0e

Commits on Jan 2, 2024

• llama : differentiate the KV dims in the attention (#4657)

  Show description for 83e633c
  

  postmasters

  and

  ggerganov

  authored
  83e633c

  Copy full SHA for 83e633c

Commits on Dec 28, 2023

• gpt2 : Add gpt2 architecture integration (#4555)

  manikbhandari

  authored
  ea5497d

  Copy full SHA for ea5497d

Commits on Dec 27, 2023

• llama : add AWQ for llama, llama2, mpt, and mistral models (#4593)

  Show description for f679349
  

  4 peopleauthored
  f679349

  Copy full SHA for f679349

Commits on Dec 24, 2023

• llama : add PLaMo model (#3557)

  Show description for 753be37
  

  okdshin

  and

  ggerganov

  authored
  753be37

  Copy full SHA for 753be37

Commits on Dec 21, 2023

• gguf-py : fix broken link

  ggerganov

  authored
  769a7bc

  Copy full SHA for 769a7bc

• py : open merges file as 'utf-8' (#4566)

  Show description for 880e352
  howlger

  authored
  880e352

  Copy full SHA for 880e352

Commits on Dec 18, 2023

• llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)

  Show description for b9e74f9
  

  4 peopleauthored
  b9e74f9

  Copy full SHA for b9e74f9

Commits on Dec 17, 2023

• gguf-py : fail fast on nonsensical special token IDs (#4489)

  cebtenzzre

  authored
  f7f468a

  Copy full SHA for f7f468a

Commits on Dec 13, 2023

• llama : add Mixtral support (#4406)

  Show description for 799a1cb
  

  3 peopleauthored
  799a1cb

  Copy full SHA for 799a1cb

Commits on Dec 12, 2023

• english : use typos to fix comments and logs (#4354)

  richardkiss

  authored
  9494d7c

  Copy full SHA for 9494d7c

Commits on Dec 1, 2023

• llama : add Qwen support (#4281)

  Show description for 37c746d
  

  simonJJJ

  and

  ggerganov

  authored
  37c746d

  Copy full SHA for 37c746d

Commits on Nov 20, 2023

• ci : add flake8 to github actions (python linting) (#4129)

  Show description for f23c035
  Galunid

  authored
  f23c035

  Copy full SHA for f23c035

Commits on Nov 19, 2023

• gguf-py : export chat templates (#4125)

  Show description for e937066
  slaren

  authored
  e937066

  Copy full SHA for e937066

Commits on Nov 17, 2023

• Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)

  Show description for 91f6499
  KerfuffleV2

  authored
  91f6499

  Copy full SHA for 91f6499

Commits on Nov 14, 2023

• stablelm : StableLM support (#3586)

  Show description for 36eed0c
  Galunid

  authored
  36eed0c

  Copy full SHA for 36eed0c

Commits on Nov 12, 2023

• gguf-py: gguf_writer: Use bytearray to build metadata (#4051)

  Show description for 21fd874
  KerfuffleV2

  authored
  21fd874

  Copy full SHA for 21fd874

Commits on Nov 11, 2023

• Fix gguf-convert-endian script (#4037)

  Show description for e86fc56
  monatis

  authored
  e86fc56

  Copy full SHA for e86fc56

• gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)

  Show description for 34b0a08
  

  KerfuffleV2

  and

  cebtenzzre

  authored
  34b0a08

  Copy full SHA for 34b0a08

Commits on Nov 7, 2023

• gguf : track writer state, free unneeded tensors, cleanup (#3871)

  cebtenzzre

  authored
  0a7c980

  Copy full SHA for 0a7c980

Commits on Nov 4, 2023

• gguf-py: Support 01.AI Yi models (#3943)

  KerfuffleV2

  authored
  f28af0d

  Copy full SHA for f28af0d

Pagination

Previous

Next