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
6baa092
•
1 Parent(s): 6f16fb3

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/runner/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -66,7 +66,7 @@
66
  "rope_theta": 10000.0,
67
  "tie_word_embeddings": false,
68
  "torch_dtype": "bfloat16",
69
- "transformers_version": "4.46.2",
70
  "use_cache": true,
71
  "vocab_size": 32000
72
  }
 
1
  {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
66
  "rope_theta": 10000.0,
67
  "tie_word_embeddings": false,
68
  "torch_dtype": "bfloat16",
69
+ "transformers_version": "4.46.3",
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": "4.46.2"
7
  }
 
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.46.3"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118c49beea93e37fb6de7e42bfb0f4f3e041aadadc4ee1e6c49ca808523a1116
3
  size 1232059012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6338c4c869c4275711ba8658c66fa065d0ab198d9f8dcadf546d950074f2c7
3
  size 1232059012