34.8 GB

Ctrl+K

1 contributor

History: 11 commits

anicka

Re-add cross-link to retrained R1-Distill-Llama 8B v12

71fb993 verified 7 days ago

.gitattributes

1.81 kB
v12 Q4_K_M GGUF for llama.cpp 7 days ago
README.md

6.34 kB
Re-add cross-link to retrained R1-Distill-Llama 8B v12 7 days ago
chat_template.jinja

14.6 kB
v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago
config.json

901 Bytes
v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago
generation_config.json

136 Bytes
v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago
karma-electric-apertus-8b-v10.1-Q4_K_M.gguf

5.06 GB
xet

Upload karma-electric-apertus-8b-v10.1-Q4_K_M.gguf with huggingface_hub about 1 month ago
karma-electric-apertus-8b-v10.1-Q8_0.gguf

8.57 GB
xet

Upload karma-electric-apertus-8b-v10.1-Q8_0.gguf with huggingface_hub about 1 month ago
karma-electric-apertus-8b-v12-Q4_K_M.gguf

5.06 GB
xet

v12 Q4_K_M GGUF for llama.cpp 7 days ago
model.safetensors

16.1 GB
xet

v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago
reward-eval.gbnf

910 Bytes
Upload reward-eval.gbnf with huggingface_hub about 1 month ago
system-prompt.txt

383 Bytes
v12 recommended system prompt 7 days ago
tokenizer.json

17.1 MB
xet

v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago
tokenizer_config.json

418 Bytes
v12: retrained on Teapot-composed v12 data (3346 examples), same recipe as KE Llama 3.1 8B v12 — model weights + tokenizer + chat template 7 days ago