Svensk Jev-lik beslutsmodell (choice/score/noul): Kev-0.6B-vikter, dataset, ONNX web-vikter, webbläsardemo. Apache-2.0.
Birger Moell
birgermoell
AI & ML interests
Ignore everyones attempts to teach you AI. AI is not the most important thing. Love is. ❤️ ❤️ ❤️
Recent Activity
updated a dataset 1 day ago
birgermoell/oellm-rl-pools published a dataset 1 day ago
birgermoell/oellm-rl-pools liked a dataset 4 days ago
marianna13/prelude-9b-posttrain-recipeOrganizations
A list of some of the papers I've written / collaborated on.
-
Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
Paper • 2404.19622 • Published • 2 -
Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support
Paper • 2405.09300 • Published -
You don't understand me!: Comparing ASR results for L1 and L2 speakers of Swedish
Paper • 2405.13379 • Published -
Evaluating Large Language Models with Human Feedback: Establishing a Swedish Benchmark
Paper • 2405.14006 • Published
Svensk Jev-lik beslutsmodell (choice/score/noul): Kev-0.6B-vikter, dataset, ONNX web-vikter, webbläsardemo. Apache-2.0.
A list of some of the papers I've written / collaborated on.
-
Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
Paper • 2404.19622 • Published • 2 -
Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support
Paper • 2405.09300 • Published -
You don't understand me!: Comparing ASR results for L1 and L2 speakers of Swedish
Paper • 2405.13379 • Published -
Evaluating Large Language Models with Human Feedback: Establishing a Swedish Benchmark
Paper • 2405.14006 • Published
spaces 12
pinned
Running
Sven i webblasaren — svensk System One
🫎
Sven-0.6B in the browser — calibrated decisions, no server
Runtime error
Agents
1
Swedish Health Source Triage
🏥
Classify health texts into source categories
Sleeping
Local-Model Arena
⚖
Compare two local LLM responses and vote
No application file
Agents
Swedish Text Complexity
📈
Sleeping
Kb Whisper Demo
🔥
kb-whisper-demo
Sleeping
1
Triplet
🌍
models 104
birgermoell/agora-9b-GGUF
Text Generation • 9B • Updated • 157
birgermoell/oellm-9b-256k-stage5-a4b-tool-rl-step48
Text Generation • 9B • Updated • 1.12k
birgermoell/oellm-9b-256k-stage5-w2-rl-step160
Text Generation • 9B • Updated • 36
birgermoell/oellm-9b-256k-reasoning-tooluse-sft-v1
Text Generation • 1B • Updated • 871
birgermoell/oellm-9b-anneal300b-tooluse-sft
Text Generation • 0.3B • Updated • 249
birgermoell/oellm-9b-threeway-dpo-full-v1
Text Generation • 0.3B • Updated • 1.01k
birgermoell/oellm-9b-threeway-dpo-step9000
Text Generation • 0.3B • Updated • 195
birgermoell/oellm-9b-math-rlvr-phase-a-32step-experimental
Text Generation • 9B • Updated • 39
birgermoell/oellm-9b-math-rlvr-canary-step16-experimental
Text Generation • 9B • Updated • 24
birgermoell/sven-web
Updated • 10
datasets 41
birgermoell/oellm-rl-pools
Viewer • Updated • 7.17k • 30
birgermoell/openeurollm-model-identity
Viewer • Updated • 1.7k • 72
birgermoell/oellm-eu-tasks
Viewer • Updated • 37.9k • 39
birgermoell/openeurollm-tool-use-v1
Viewer • Updated • 159k • 229
birgermoell/openeurollm-reasoning-instruct-v1
Viewer • Updated • 1.17M • 692
birgermoell/oellm-excellent-dpo-v0.1
Viewer • Updated • 74k • 150
birgermoell/swedish-personas
Viewer • Updated • 100k • 65
birgermoell/medqa-reasoning-traces
Viewer • Updated • 12.7k • 642
birgermoell/sven-data
Viewer • Updated • 4.64k • 56
birgermoell/oellm-dpo-metadataset
Viewer • Updated • 65 • 80