Block or Report
Block or report BruceMacD
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
jmorganca/ollama
jmorganca/ollama PublicGet up and running with Llama 2 and other large language models locally
-
infrahq/infra
infrahq/infra PublicInfra provides authentication and access management to servers and Kubernetes clusters.
-
-
Adversarial-Faces
Adversarial-Faces PublicTesting the effectiveness of practical implementations of adversarial examples against facial recognition.
-
Face-Swap-OpenCV
Face-Swap-OpenCV PublicA basic face-swap implementation using OpenCV and dlib.
1,808 contributions in the last year
Day of Week | December Dec | January Jan | February Feb | March Mar | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | ||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Activity overview
Contribution activity
December 2023
Created 30 commits in 3 repositories
Created a pull request in jmorganca/ollama that received 3 comments
chat api endpoint
add a new /api/chat
API endpoint that takes an array of message
objects. This endpoint is an alternative to /api/generate
.
deprecate generation co…
Opened 15 other pull requests in 1 repository
jmorganca/ollama
3
open
11
merged
1
closed
-
allow for starting llava queries with filepath
This contribution was made on Dec 15
-
update required go version
This contribution was made on Dec 15
-
send empty messages on last chat response
This contribution was made on Dec 14
-
remove sample_count from docs
This contribution was made on Dec 14
-
restore model load duration on generate response
This contribution was made on Dec 14
-
exponential back-off
This contribution was made on Dec 12
-
retry on concurrent request failure
This contribution was made on Dec 12
-
fix: parallel queueing race condition caused silent failure
This contribution was made on Dec 9
-
fix: retry on concurrent request failure
This contribution was made on Dec 9
-
document response in modelfile template variables
This contribution was made on Dec 8
-
post-response templating
This contribution was made on Dec 8
-
fix: only flush template in chat when current role encountered
This contribution was made on Dec 8
-
fix: restore modelfile system in prompt template
This contribution was made on Dec 8
-
fix: encode full previous prompt in context
This contribution was made on Dec 8
-
os specific ctrl-z
This contribution was made on Dec 7
Reviewed 27 pull requests in 1 repository
jmorganca/ollama
25 pull requests
-
Add cgo implementation for llama.cpp
This contribution was made on Dec 19
-
add lint and test on pull_request
This contribution was made on Dec 18
-
allow for starting llava queries with filepath
This contribution was made on Dec 18
-
add API create/copy handlers
This contribution was made on Dec 15
-
README with Enchanted iOS App
This contribution was made on Dec 15
-
Added Bionic GPT as a front end.
This contribution was made on Dec 15
-
send empty messages on last chat response
This contribution was made on Dec 15
-
Add unit test of API routes
This contribution was made on Dec 14
-
Added message format for chat api
This contribution was made on Dec 13
-
post-response templating
This contribution was made on Dec 13
-
add image support to the chat api
This contribution was made on Dec 12
-
Fix issues with
/set template
and/set system
This contribution was made on Dec 12 -
retry on concurrent request failure
This contribution was made on Dec 12
-
Fix Readme "Database -> MindsDB" link
This contribution was made on Dec 12
-
Update README.md
This contribution was made on Dec 11
-
remove per-model types
This contribution was made on Dec 11
-
fix: parallel queueing race condition caused silent failure
This contribution was made on Dec 9
-
Multimodal support
This contribution was made on Dec 8
-
Simple chat example for typescript
This contribution was made on Dec 7
-
fix redundant newline
This contribution was made on Dec 7
-
Simple chat example
This contribution was made on Dec 6
-
fix: trim space in modelfile fields
This contribution was made on Dec 5
-
revert cli to use /api/generate
This contribution was made on Dec 5
-
Added
docker-compose.yaml
This contribution was made on Dec 4 -
Add
/chat
APIThis contribution was made on Dec 4 - Some pull request reviews not shown.
Created an issue in jmorganca/ollama that received 4 comments
Update VRAM layer offloading to account for context size
Our current calculation for the amount of layers to offload to VRAM does not account for context size, so large context models may fail to load if …
Opened 2 other issues in 1 repository
jmorganca/ollama
2
open
-
Submitting an image as the first argument in a prompt to a LLaVA model results in
Unknown command
This contribution was made on Dec 13 -
Allow Response Templating
This contribution was made on Dec 7