10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 511 ms
- 1q2.5_7b_aime_per_chunk_act_untrained_500demo or tutorialno passport yet
modelrecord20 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- nelsonjchen/minigpt-4_vicuna-7b
MiniGPT-4 w/ Vicuna-7B (Image Question/Captioning Use)
- nelsonjchen/minigpt-4_vicuna-7b
modelrecord
- meta/llama-2-7b
Base version of Llama 2 7B, a 7 billion parameter language model
- meta/llama-2-7b
modelrecord
- google-deepmind/gemma-7b
7B base version of Google’s Gemma model
- google-deepmind/gemma-7b
modelrecord
- joehoover/zephyr-7b-alpha
A high-performing language model trained to act as a helpful assistant
- joehoover/zephyr-7b-alpha
modelrecord
- lucataco/vicuna-7b-v1.3
lmsys/vicuna-7b-v1.3
- lucataco/vicuna-7b-v1.3
modelrecord
- lucataco/llama-2-7b-chat
Meta's Llama 2 7b Chat - GPTQ
- lucataco/llama-2-7b-chat
modelrecord
- kcaverly/neuralbeagle14-7b-gguf
NeuralBeagle14-7B is (probably) the best 7B model you can find!
- kcaverly/neuralbeagle14-7b-gguf
modelrecord
- andreasjansson/llama-2-7b-embeddings
Llama2 7B with embedding output
- andreasjansson/llama-2-7b-embeddings
modelrecord190 downloads/month
- robotics
Task: robotics
- robotics
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.