Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W8A8-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
ad811f2
·
verified ·
1 Parent(s): 73a45d0

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
config.json CHANGED
@@ -53,7 +53,7 @@
53
  }
54
  },
55
  "format": "int-quantized",
56
- "global_compression_ratio": 1.4555025329431568,
57
  "ignore": [
58
  "lm_head"
59
  ],
@@ -66,7 +66,7 @@
66
  "rope_theta": 10000.0,
67
  "tie_word_embeddings": false,
68
  "torch_dtype": "bfloat16",
69
- "transformers_version": "4.47.1",
70
  "use_cache": true,
71
  "vocab_size": 32000
72
  }
 
53
  }
54
  },
55
  "format": "int-quantized",
56
+ "global_compression_ratio": 1.5236665854369158,
57
  "ignore": [
58
  "lm_head"
59
  ],
 
66
  "rope_theta": 10000.0,
67
  "tie_word_embeddings": false,
68
  "torch_dtype": "bfloat16",
69
+ "transformers_version": "4.48.0",
70
  "use_cache": true,
71
  "vocab_size": 32000
72
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.47.1"
7
  }
 
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.48.0"
7
  }