jtatman/hermes_agent_llama_1b_uncensored_grpo-bucket
4.21 MB
James PRO
jtatman
AI & ML interests
improving domain specific models and re-sampling data, refining datasets for use in different modalities, small scale micro-llm clusters using quantized and smoothed models, and all emerging llm stack connecting technologies. Small models rock.
Recent Activity
liked a model about 21 hours ago
openbmb/MiniCPM5-2B liked a model about 21 hours ago
AlicanKiraz0/BaronLLM-v2-OffensiveSecurityLLM-Q8 published a Space 12 days ago
jtatman/customer-message-triageOrganizations
Small Models Fine-Tuned for Action
-
jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser
Text Generation • 2B • Updated • 47 • • 7 -
jtatman/TinyDolphin-3x-MoE
Text Generation • 3B • Updated • 249 • 1 -
jtatman/Reyna-Mini-1.8B-v0.2-cosmopedia-laser
Text Generation • 2B • Updated • 14 -
jtatman/tinydolphin-3x-MoE-samantha-chatml-therabot
Text Generation • 3B • Updated • 16 • 1
Small Models Fine-Tuned for Action
-
jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser
Text Generation • 2B • Updated • 47 • • 7 -
jtatman/TinyDolphin-3x-MoE
Text Generation • 3B • Updated • 249 • 1 -
jtatman/Reyna-Mini-1.8B-v0.2-cosmopedia-laser
Text Generation • 2B • Updated • 14 -
jtatman/tinydolphin-3x-MoE-samantha-chatml-therabot
Text Generation • 3B • Updated • 16 • 1
quantized models that will run on almost anything
spaces 5
Sleeping
Agents
Customer Message Triage
📨
Translate and triage a customer message, live, on ZeroGPU
Running
Agents
Hermes Agent Llama 1b Uncensored Grpo
🎯
Display an interactive tracking dashboard
Runtime error
Agents
Tiny Dolphin Moe 3x Therapist
💬
demonstration of the model with psychological dataset
Running
Video Object Detection
📷
Real-time object detection w/ 🤗 Transformers.js
Build error
2
dolphin-2.2.1-mistral-7B-GGUF (Q6_K)
🚀
models 168
jtatman/qwen_3_4b_mythos_finetune_gguf
4B • Updated • 126
jtatman/qwen_3_4b_mythos_finetune_16bit
Text Generation • 4B • Updated • 8
jtatman/llama-3.2-1b-breadcrumbs-uncensismegistus-dolphinseek
Text Generation • 1B • Updated • 17 • 1
jtatman/llama3.2-1b-5x-MoE-uncensored-code-reason-tool-agent
4B • Updated • 8
jtatman/llama3.2_1b_uncensored_pentest_grpo-merged
Text Generation • 1B • Updated • 14
jtatman/llama3.2_1b_uncensored_pentest_grpo
Updated
jtatman/llama3.2_1b_2025_uncensored_v2-GRPO
Updated
jtatman/finetuning-twitter-finance-sentiment-distilbert-2-epoch
Text Classification • 67M • Updated • 8
jtatman/finetuning-twitter-finance-sentiment-distilbert
Text Classification • 67M • Updated • 8
jtatman/finetuning-twitter-sentiment-distilbert
Text Classification • 67M • Updated • 12
datasets 97
jtatman/ml-portfolio-assets
Updated • 5
jtatman/curated-v2-combined-sft
Viewer • Updated • 3.48k • 22
jtatman/curated-v2-combined-dpo-bootstrap
Viewer • Updated • 3.48k • 9
jtatman/one_twenty_five_faces
Viewer • Updated • 20.1k • 32
jtatman/lwd_mental_occult_preprocess
Viewer • Updated • 18.3k • 14
jtatman/movie_sentiment_reviews
Viewer • Updated • 1k • 6
jtatman/myers_briggs_combined
Viewer • Updated • 216k • 21
jtatman/myers_briggs_text_classify
Viewer • Updated • 8.68k • 96
jtatman/myers_briggs_description_classify
Viewer • Updated • 160k • 14 • 1
jtatman/mental_health_psychology_curated_alpaca
Viewer • Updated • 4.8k • 25 • 6