Trelis
/

Llama-2-7b-chat-hf-hosted-inference-8bit

Text Generation

hosted inference

8-bit precision

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Llama-2-7b-chat-hf-hosted-inference-8bit

2 contributors

History: 10 commits

RonanMcGovern's picture

SFconvertbot's picture

Adding `safetensors` variant of this model (#1)

6e9d874 about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

11.2 kB

update notes on inference about 1 year ago
config.json

981 Bytes

Upload LlamaForCausalLM about 1 year ago
generation_config.json

132 Bytes

Upload LlamaForCausalLM about 1 year ago
model.safetensors

7.01 GB
LFS

Adding `safetensors` variant of this model (#2) about 1 year ago
pytorch_model.bin
Detected Pickle imports (5)
- "collections.OrderedDict",
- "torch.CharStorage",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage"
What is a pickle import?
7.01 GB
LFS

Upload LlamaForCausalLM about 1 year ago
pytorch_model.bin.index.json

26.8 kB

Upload LlamaForCausalLM about 1 year ago
special_tokens_map.json

414 Bytes

Upload tokenizer about 1 year ago
tokenizer.json

1.84 MB

Upload tokenizer about 1 year ago
tokenizer.model

500 kB
LFS

Upload tokenizer about 1 year ago
tokenizer_config.json

725 Bytes

Upload tokenizer about 1 year ago