Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W8A8_tensor_weight_static_per_tensor_act-e2e

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
8-bit precision
compressed-tensors
Model card Files Community
nm-autobot commited on
Commit
1bf83b9
•
1 Parent(s): 771160e

Upload LlamaForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
config.json CHANGED
@@ -60,7 +60,7 @@
60
  "kv_cache_scheme": null,
61
  "quant_method": "compressed-tensors",
62
  "quantization_status": "compressed",
63
- "version": "0.6.0.20241002"
64
  },
65
  "rms_norm_eps": 1e-05,
66
  "rope_scaling": null,
 
60
  "kv_cache_scheme": null,
61
  "quant_method": "compressed-tensors",
62
  "quantization_status": "compressed",
63
+ "version": "0.6.0.20241003"
64
  },
65
  "rms_norm_eps": 1e-05,
66
  "rope_scaling": null,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3626910745e94f57eecd846065c356351f75348b0256af34434b29c71aec0f2
3
  size 1231270112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9ab94099775f9b0ceebefdc2feaac06402e509ec8b6f48cff4eacb94e77949
3
  size 1231270112