Ctrl+K

1 contributor

config: integer bits in quantization_config (hub schema fix); original 4.03bpw tuning preserved under native_quantization_config

f316d3d verified 9 days ago

.gitattributes

1.77 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
CONVERT.log

4.75 MB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
GATE_exllamav3.json

1.55 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
LICENSE

1.07 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
README.md

8.07 kB
model card: model_name (the pack's own id, served by /v1/models), base_model = the original model, base_model_relation: quantized 16 days ago
RECIPE.yaml

1.66 MB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
SHA256SUMS

3.5 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
chat_template.jinja

7.76 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
config.json

3.67 kB
config: integer bits in quantization_config (hub schema fix); original 4.03bpw tuning preserved under native_quantization_config 9 days ago
configuration_naive_n05_flash.py

7.27 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
generation_config.json

172 Bytes
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
merges.txt

1.67 MB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00001-of-00024.safetensors

8.09 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00002-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00003-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00004-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00005-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00006-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00007-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00008-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00009-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00010-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00011-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00012-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00013-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00014-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00015-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00016-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00017-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00018-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00019-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00020-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00021-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00022-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00023-of-00024.safetensors

6.61 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model-00024-of-00024.safetensors

3.78 GB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
model.safetensors.index.json

13.5 MB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
modeling_naive_n05_flash.py

12.7 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
quantization_config.json

44.7 MB
xet

EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
special_tokens_map.json

406 Bytes
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
tokenizer.json

7.03 MB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
tokenizer_config.json

5.64 kB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
vocab.README.md

61 Bytes
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago
vocab.json

2.78 MB
EXL3 4 bpw (experts 4 / attention 6) from bf16, code calibration 17 days ago