Snowflake
/

Llama-3.1-SwiftKV-8B-Instruct-FP8

compressed-tensors

Model card Files Files and versions

Llama-3.1-SwiftKV-8B-Instruct-FP8

11.6 GB

Ctrl+K

Ctrl+K

3 contributors

History: 23 commits

aurick's picture

Set max_position_embeddings to 8192

abc2801 verified 12 months ago

.gitattributes

1.52 kB
initial commit over 1 year ago
README.md

3.73 kB
add scarf over 1 year ago
config.json

2.07 kB
Set max_position_embeddings to 8192 12 months ago
figure-4-full.png

230 kB
full figure 4 from blog over 1 year ago
figure-4.png

89.7 kB
figure 4 from blog over 1 year ago
figure-6.png

419 kB
figure 6 from blog over 1 year ago
generation_config.json

155 Bytes
Upload generation_config.json with huggingface_hub over 1 year ago
model-00001-of-00003.safetensors

4.98 GB
xet

Upload model-00001-of-00003.safetensors with huggingface_hub over 1 year ago
model-00002-of-00003.safetensors

4.51 GB
xet

Upload model-00002-of-00003.safetensors with huggingface_hub over 1 year ago
model-00003-of-00003.safetensors

2.1 GB
xet

Upload model-00003-of-00003.safetensors with huggingface_hub over 1 year ago
model.safetensors.index.json

52.6 kB
Upload model.safetensors.index.json with huggingface_hub over 1 year ago
recipe.yaml

134 Bytes
Upload recipe.yaml with huggingface_hub over 1 year ago
special_tokens_map.json

439 Bytes
Upload special_tokens_map.json with huggingface_hub over 1 year ago
tokenizer.json

9.09 MB
Upload tokenizer.json with huggingface_hub over 1 year ago
tokenizer_config.json

55.4 kB
Upload tokenizer_config.json with huggingface_hub over 1 year ago