Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W8A8_channel_weight_static_per_tensor-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
b9e7527
•
1 Parent(s): 93d567a

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": "0.6.0.20240928"
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": "0.6.0.20240929"
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:a6e7dd01f726bae94988a632b681bcdbbfe122ae602b680c5a207f21a9c93f7e
3
  size 1232059012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9431a505d3b5ea7b6dfaab9f4381d463654f463b4f2a1ebb0fda32bfadc660cb
3
  size 1232059012