intrect/VELA at main

VELA

43.3 GB

1 contributor

History: 12 commits

intrect's picture

fix: change tokenizer_class to Qwen2TokenizerFast for vLLM compatibility

ecf8e6b verified about 11 hours ago

.gitattributes
1.67 kB

feat: add Q8_0 GGUF quantized model (7.6GB) 2 days ago
README.md
8.05 kB

docs: update training data distribution with accurate numbers (SFT 36,713 + DPO 24,779) 2 days ago
added_tokens.json
605 Bytes

Upload folder using huggingface_hub 17 days ago
chat_template.jinja
2.51 kB

Upload folder using huggingface_hub 17 days ago
config.json
701 Bytes

Fix config.json for vLLM compatibility (remove layer_types, fix rope_parameters) 17 days ago
generation_config.json
242 Bytes

Update to DPO v4 merged model 17 days ago
merges.txt
1.67 MB

Upload folder using huggingface_hub 17 days ago
model-00001-of-00004.safetensors
4.88 GB
xet

Upload folder using huggingface_hub 17 days ago
model-00002-of-00004.safetensors
4.93 GB
xet

Upload folder using huggingface_hub 17 days ago
model-00003-of-00004.safetensors
4.33 GB
xet

Upload folder using huggingface_hub 17 days ago
model-00004-of-00004.safetensors
1.09 GB
xet

Upload folder using huggingface_hub 17 days ago
model.safetensors
15.2 GB
xet

Update to DPO v4 merged model 17 days ago
model.safetensors.index.json
27.8 kB

Upload folder using huggingface_hub 17 days ago
special_tokens_map.json
613 Bytes

Upload folder using huggingface_hub 17 days ago
tokenizer.json
11.4 MB
xet

Update to DPO v4 merged model 17 days ago
tokenizer_config.json
370 Bytes

fix: change tokenizer_class to Qwen2TokenizerFast for vLLM compatibility about 11 hours ago
vela-q4_k_m.gguf
4.68 GB
xet

feat: add Q4_K_M GGUF quantized model (4.4GB) 2 days ago
vela-q8_0.gguf
8.1 GB
xet

feat: add Q8_0 GGUF quantized model (7.6GB) 2 days ago
vocab.json
2.78 MB

Upload folder using huggingface_hub 17 days ago