rajkosto
/

Meta-Llama-3-8B-Instruct

Text Generation

text-generation-inference

Model card Files Files and versions

Meta-Llama-3-8B-Instruct

27.6 GB

1 contributor

History: 5 commits

rajkosto's picture

Add proper pre-tokenization fixed BPE version

830fae1 verified over 1 year ago

.gitattributes
1.73 kB

Add proper pre-tokenization fixed BPE version over 1 year ago
LICENSE.txt
7.8 kB

Copy aux files from Llama3 main repo over 1 year ago
Meta-Llama-3-8B-Instruct.Q4_K_M.gguf
4.92 GB
xet

Add proper pre-tokenization fixed BPE version quantized with Q4_K_M over 1 year ago
Meta-Llama-3-8B-Instruct.Q6_K.gguf
6.6 GB
xet

Add proper pre-tokenization fixed BPE version quantized with Q6_K over 1 year ago
Meta-Llama-3-8B-Instruct.f16.gguf
16.1 GB
xet

Add proper pre-tokenization fixed BPE version over 1 year ago
README.md
39.1 kB

Copy aux files from Llama3 main repo over 1 year ago
USE_POLICY.md
4.7 kB

Copy aux files from Llama3 main repo over 1 year ago
config.json
654 Bytes

Copy aux files from Llama3 main repo over 1 year ago
generation_config.json
187 Bytes

Copy aux files from Llama3 main repo over 1 year ago
gitattributes.txt
1.52 kB

Copy aux files from Llama3 main repo over 1 year ago
model.safetensors.index.json
24 kB

Copy aux files from Llama3 main repo over 1 year ago
special_tokens_map.json
73 Bytes

Copy aux files from Llama3 main repo over 1 year ago
tokenizer.json
9.09 MB

Copy aux files from Llama3 main repo over 1 year ago
tokenizer_config.json
51 kB

Copy aux files from Llama3 main repo over 1 year ago