Commits

History for

Commits on May 28, 2024

gguf-py, llama : whitespace formatting fixes
sszymczy
committedMay 28, 2024

Commits on May 24, 2024

Commits on May 23, 2024

ggml : drop support for QK_K=64 (ggerganov#7473 )
ggerganov
committedMay 23, 2024

Commits on May 21, 2024

llama : add phi3 128K model support (ggerganov#7225 )

liuwei-git
and
ggerganov
committedMay 21, 2024

Commits on May 20, 2024

Added YaRN log multiplier model header parameter corresponding to the multiplier of the ln(s) from the sqrt(1/t) = 0.1 ln(s) + 1 equation.
sszymczy
committedMay 20, 2024
llama : remove Persimmon (ggerganov#7408 )
ggerganov
committedMay 20, 2024

Commits on May 19, 2024

Added expert_weights_scale parameter for scaling MoE gate weights.
sszymczy
committedMay 19, 2024

Commits on May 18, 2024

Added initial support for DeepSeek-V2-Lite model.
sszymczy
committedMay 18, 2024
Added five new DeepSeek-V2-specific parameters:
sszymczy
committedMay 18, 2024

Commits on May 16, 2024

Added initial support for DeepseekV2ForCausalLM.
sszymczy
committedMay 16, 2024

Commits on May 11, 2024

convert-hf : support bfloat16 conversion (ggerganov#7158 )
compilade
committedMay 11, 2024
llama : add Jina Embeddings architecture (ggerganov#6826 )

JoanFM
and
ggerganov
committedMay 11, 2024

Commits on May 8, 2024

convert-hf : save memory with lazy evaluation (ggerganov#7075 )
compilade
committedMay 8, 2024
ggml : introduce bfloat16 support (ggerganov#6412 )
jart
committedMay 8, 2024

Commits on May 3, 2024

convert.py : add python logging instead of print() (ggerganov#6511 )
mofosyne
committedMay 3, 2024

Commits on Apr 29, 2024

llama : fix BPE pre-tokenization (ggerganov#6920 )

committedApr 29, 2024

Commits on Apr 24, 2024

llama : add phi3 support (ggerganov#6852 )

liuwei-git
and
ggerganov
committedApr 24, 2024

Commits on Apr 21, 2024

gguf-py : add IQ1_M to GGML_QUANT_SIZES (ggerganov#6761 )
pmysl
committedApr 21, 2024

Commits on Apr 19, 2024

Implement the OLMo architecture (ggerganov#6741 )
nopperl
committedApr 19, 2024

Commits on Apr 18, 2024

convert : support models with multiple chat templates (ggerganov#6588 )
CISC
committedApr 18, 2024

Commits on Apr 16, 2024

llama : add StableLM2 12B (ggerganov#6635 )

ashishdatta
and
compilade
committedApr 16, 2024
llama : add qwen2moe (ggerganov#6074 )

simonJJJ
and
ggerganov
committedApr 16, 2024
gguf : add special tokens metadata for FIM/Infill (ggerganov#6689 )
danbev
committedApr 16, 2024

Commits on Apr 13, 2024

model: support arch DbrxForCausalLM (ggerganov#6515 )

phymbert
and
megha95
committedApr 13, 2024

Commits on Apr 9, 2024

llama : add Command R Plus support (ggerganov#6491 )

committedApr 9, 2024

Commits on Apr 5, 2024

gguf.py : add licence and version to gguf writer (ggerganov#6504 )
mofosyne
committedApr 5, 2024

Commits on Apr 3, 2024

llama : add SEA-LION support (ggerganov#6448 )

committedApr 3, 2024
ggml : mul_mat_id use the same tensor for all the experts (ggerganov#6387 )

slaren
and
ggerganov
committedApr 3, 2024

Commits on Mar 29, 2024

[Model] Add support for xverse (ggerganov#6301 )

committedMar 29, 2024

Commits on Mar 26, 2024

IQ1_M: 1.75 bpw quantization (ggerganov#6302 )

ikawrakow
and
Kawrakow
committedMar 26, 2024

Commits on Mar 23, 2024

llama : add grok-1 support (ggerganov#6204 )

arki05
and
ggerganov
committedMar 23, 2024

Commits on Mar 15, 2024

llama : add Command-R support (ggerganov#6033 )
acanis
committedMar 15, 2024
gguf : add support for I64 and F64 arrays (ggerganov#6062 )
certik
committedMar 15, 2024