Open Issues Need Help
View All on GitHub bug help wanted good first issue difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
ship: _fail escapes markup but lets control bytes through to the terminal (after #1776) about 6 hours ago
bug good first issue claimed difficulty:1
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
backend: unsloth is accepted and silently ignored for task: distill about 6 hours ago
bug help wanted claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
training.gradient_checkpointing is decided by the trainer, not the config: `false` cannot turn it off on any 4-bit run, and 9 trainers can drop `true` about 6 hours ago
bug help wanted claimed difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`preference_loss_weights` never blends: only the primary loss trains, because the wrapper reads log-probs from the batch about 6 hours ago
bug help wanted claimed difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
eval gate: an integer baseline score too large for a float raises OverflowError instead of a usage error (after #1779) about 8 hours ago
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
cli: model and output paths printed next to sanitized text are still raw Rich markup in chat, diff and eval human (after #1602) about 9 hours ago
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
pixtral-dpo recipe cannot train: format llava rows reach DPO as messages+image, and the config loads clean about 9 hours ago
bug help wanted difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
configs: 30 shipped grpo/ipo/bco/reward_model/online_dpo configs leave gradient_checkpointing unset and now run without it (after #1778) about 10 hours ago
bug help wanted good first issue difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
terminal: for_terminal should strip bidi controls and invisible separators (keep ZWJ and ZWNJ) about 11 hours ago
bug help wanted difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
data: a JSONL line that is valid JSON but not an object crashes review, inspect, validate, stats and dedup with AttributeError about 11 hours ago
bug help wanted difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
data: a path or flag containing Rich markup crashes soup data review (MarkupError) and is mangled elsewhere about 11 hours ago
bug help wanted difficulty:3
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`task: unlearn` on `backend: mlx` refuses with "(deferred to v0.61.1)", a release promise that expired 14 versions ago about 11 hours ago
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Failures skip cleanup: multi-GB export merge dirs, extracted cans, stuck `running` sweep rows, a live Aider container about 15 hours ago
bug help wanted difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`training.citation_faithful` is accepted on `task: pretrain` but the pretrain trainer never reads it 1 day ago
bug help wanted difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`soup doctor --config` has declared tables for 3 of the 19 combinations the shipped recipes use 1 day ago
enhancement help wanted difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted claimed difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
tests: pin the accept-time rollout check and the pre-record flush of the canary stats batch 1 day ago
help wanted good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
help wanted qa difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
[QA] Verify HuggingFace Hub push + Spaces deploy (push, train --push-as, data push, deploy hf-space) 6 days ago
help wanted qa difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:9
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:9
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`soup train --cloud lambda`: print the tail of the remote log before the instance is terminated 6 days ago
enhancement help wanted claimed difficulty:3
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
documentation good first issue claimed difficulty:1
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`soup train --cloud`: upload local input files so the default `soup init` flow works with local data 6 days ago
enhancement help wanted difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
v0.63.1: Live SaaS pull adapters for soup ingest (Langfuse/LangSmith/Helicone/OpenPipe API SDKs) 6 days ago
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Cloud training: add a RunPod backend behind 'soup train --cloud' (Lambda shipped in #528) 7 days ago
enhancement help wanted difficulty:8
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
help wanted good first issue claimed difficulty:1
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:3
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`training.lora.use_dora` loads on `backend: unsloth` and `backend: mlx` but is never applied 7 days ago
bug help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
documentation good first issue claimed difficulty:1
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`task: unlearn` finishes training and then dies with `KeyError: 'duration'` in the completion panel 7 days ago
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Friendly-error 401/403 patterns backtrack quadratically on "HTTP" plus a long whitespace run 7 days ago
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:4
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed difficulty:2
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:8
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:6
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:9
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Fast-LoRA autograd: LoRA on q/k/v with one shared X (concatenated A, one dX accumulation) 7 days ago
enhancement help wanted difficulty:9
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Fast-LoRA autograd: fused LoRA MLP block (gate/up/down around SwiGLU) with a hand-written backward 7 days ago
enhancement help wanted difficulty:9
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted difficulty:5
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted upstream-gated difficulty:8
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted infra-blocked difficulty:7
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted good first issue
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
One loopback set for every outbound gate 9 days ago
enhancement good first issue
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
enhancement help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
Say what to do in the private-address refusal 11 days ago
enhancement good first issue claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
A judge that is down still costs 3 s of backoff per row, so a long judged run does not stop early 12 days ago
enhancement help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
`freeze_layers` / `freeze_ratio` are accepted on every task but only `task: sft` applies them 13 days ago
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug help wanted
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers
bug good first issue claimed
MakazhanAlpamys/Soup MakazhanAlpamys/Soup Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Open project →
72
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Python
#artificial-intelligence#cli#dpo#fine-tuning#finetuning#gguf#huggingface#llm#llmops#local-llm#lora#machine-learning#model-finetuning#ollama#peft#python#pytorch#qlora#sft#transformers