GitLab

The `stop` option to the generate API is a list of sequences that should cause generation to stop. Although these are commonly called "stop tokens", they do not necessarily correspond to LLM tokens (per the LLM's tokenizer). For example, if the caller sends a generate request with `"stop":["\n"]`, then generation should stop on any token containing `\n` (and trim `\n` from the output), not just if the token exactly matches `\n`. If `stop` were interpreted strictly as LLM tokens, then it would require callers of the generate API to know the LLM's tokenizer and enumerate many tokens in the `stop` list.

Fixes https://github.com/jmorganca/ollama/issues/295.

update upload chunks

allow F16 to use metal

update README.md

add 34b to mem check

set default template

warning F16 uses significantly more memory than quantized model so the
standard requires don't apply.

Previously, `ollama rm model1 model2 modelN` would only delete `model1`. The other model command-line arguments would be silently ignored. Now, all models mentioned are deleted.

patch llama.cpp for 34B

add 34b model type

Mxyng/cleanup

use url.URL

build release mode

add version

retry on unauthorized chunk push

copy metadata from source

The token printed for authorized requests has a lifetime of 1h. If an
upload exceeds 1h, a chunk push will fail since the token is created on
a "start upload" request.

This replaces the Pipe with SectionReader which is simpler and
implements Seek, a requirement for makeRequestWithRetry. This is
slightly worse than using a Pipe since the progress update is directly
tied to the chunk size instead of controlled separately.