Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / c0sogi/llama-api issues and pull requests
#29 - FastAPI + llamapi issue
Issue -
State: open - Opened by Samraw003 6 months ago
#28 - Stopped working after enabling CUDA
Issue -
State: open - Opened by alexellis 10 months ago
#27 - High RAM and CPU usage
Issue -
State: open - Opened by delta-whiplash 11 months ago
#26 - Usage of embedding through langchain
Issue -
State: open - Opened by jordandroid 11 months ago
#25 - Support min_p sampler
Issue -
State: open - Opened by atisharma 12 months ago
#24 - How can I use a specific prompt template?
Issue -
State: open - Opened by Dougie777 about 1 year ago
#23 - how to run this api in cpu only mode
Issue -
State: open - Opened by delta-whiplash about 1 year ago
- 1 comment
#22 - Zephyr7b gives gobbly gook output but Mistral7b works fine.
Issue -
State: open - Opened by Dougie777 about 1 year ago
#21 - exllama GPU split
Issue -
State: open - Opened by atisharma about 1 year ago
- 1 comment
#20 - exllamav2
Issue -
State: open - Opened by ehartford about 1 year ago
- 2 comments
#19 - Any way to define embeddings model in model_definitions.py?
Issue -
State: open - Opened by morgendigital about 1 year ago
- 1 comment
#18 - Long generations dont return data but server says 200 OK. Swagger screen just says LOADING forever.
Issue -
State: open - Opened by Dougie777 about 1 year ago
- 5 comments
#17 - BUG: I found the model path bug!
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 2 comments
#16 - Set number of cores being used on cpu?
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 2 comments
#15 - Support for ExLlama V2
Issue -
State: closed - Opened by Immortalin about 1 year ago
- 2 comments
#14 - Generation stops at 251 tokens - works fine on oobabooga
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 3 comments
#13 - warning: failed to mlock 245760-byte buffer (after previously locking 0 bytes): Cannot allocate memory llm_load_tensors: mem required = 46494.72 MB (+ 1280.00 MB per state)
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 4 comments
#12 - model_definitions.py
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 3 comments
#11 - Is there a way to use this on google Colab and have the url be public?
Issue -
State: open - Opened by ashercn97 about 1 year ago
- 1 comment
#10 - Dumb question: definitions.py model parameters
Issue -
State: closed - Opened by Dougie777 about 1 year ago
- 2 comments
#9 - Proxy to openAI
Issue -
State: open - Opened by kreolsky about 1 year ago
- 2 comments
#8 - Using with LangChain instead openai API
Issue -
State: open - Opened by kreolsky about 1 year ago
- 1 comment
#7 - Dev update (23.9.3.)
Pull Request -
State: closed - Opened by c0sogi about 1 year ago
#6 - Dev update (23.8.27.)
Pull Request -
State: closed - Opened by c0sogi about 1 year ago
#5 - Dev update (23.8.22.)
Pull Request -
State: closed - Opened by c0sogi about 1 year ago
#4 - Dev update (23.8.17.)
Pull Request -
State: closed - Opened by c0sogi about 1 year ago
#3 - Dev update (23.8.9.)
Pull Request -
State: closed - Opened by c0sogi over 1 year ago
#2 - Huggingface downloader & Simpler log message & InterruptMixin
Pull Request -
State: closed - Opened by c0sogi over 1 year ago
#1 - Dependency solution
Pull Request -
State: closed - Opened by c0sogi over 1 year ago