18.8 GB

Ctrl+K

1 contributor

History: 20 commits

Maxtimer97

Changed to correct architecture name for vllm

d97e95b verified 6 months ago

ops
Relative import first 6 months ago
.gitattributes

1.52 kB
initial commit 6 months ago
README.md

5.17 kB
Upload ChatGLMForConditionalGeneration 6 months ago
added_tokens.json

356 Bytes
Upload tokenizer 6 months ago
chat_template.jinja

2.89 kB
Upload tokenizer 6 months ago
compressed_attention.py

42.4 kB
Added num stages tuning 6 months ago
config.json

1.61 kB
Changed to correct architecture name for vllm 6 months ago
configuration_chatglm.py

2.81 kB
Added attn_imp in config 6 months ago
generation_config.json

155 Bytes
Upload ChatGLMForConditionalGeneration 6 months ago
model-00001-of-00004.safetensors

4.99 GB
xet

Upload ChatGLMForConditionalGeneration 6 months ago
model-00002-of-00004.safetensors

4.9 GB
xet

Upload ChatGLMForConditionalGeneration 6 months ago
model-00003-of-00004.safetensors

4.9 GB
xet

Upload ChatGLMForConditionalGeneration 6 months ago
model-00004-of-00004.safetensors

4.03 GB
xet

Upload ChatGLMForConditionalGeneration 6 months ago
model.safetensors.index.json

37 kB
Upload ChatGLMForConditionalGeneration 6 months ago
modeling_chatglm.py

59 kB
Corrected device assignment error 6 months ago
pooling.py

6.05 kB
Flattened repo 6 months ago
special_tokens_map.json

601 Bytes
Upload tokenizer 6 months ago
tokenization_chatglm.py

8.99 kB
Upload tokenizer 6 months ago
tokenizer.model

2.62 MB
xet

Upload tokenizer 6 months ago
tokenizer_config.json

3.23 kB
Upload tokenizer 6 months ago
topk_sparse_attention.py

40.2 kB
Changed to autotune triton for 48G GPU deployment 6 months ago
utils.py

1.43 kB
Flattened repo 6 months ago