Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W4A16_2of4-e2e

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
nm-autobot commited on
Commit
844b20d
•
1 Parent(s): a9f3355

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
@@ -51,7 +51,7 @@
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
- "global_sparsity": 0.44618110215038337,
55
  "ignore": [
56
  "lm_head"
57
  ],
@@ -67,7 +67,7 @@
67
  "rope_theta": 10000.0,
68
  "tie_word_embeddings": false,
69
  "torch_dtype": "bfloat16",
70
- "transformers_version": "4.46.1",
71
  "use_cache": true,
72
  "vocab_size": 32000
73
  }
 
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
+ "global_sparsity": 0.44618086990238054,
55
  "ignore": [
56
  "lm_head"
57
  ],
 
67
  "rope_theta": 10000.0,
68
  "tie_word_embeddings": false,
69
  "torch_dtype": "bfloat16",
70
+ "transformers_version": "4.46.2",
71
  "use_cache": true,
72
  "vocab_size": 32000
73
  }
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": "4.46.1"
7
  }
 
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.46.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39ff65deba6684e10af8b7e59ebc64c58a385755f0f91680ab726bf33a5d36ce
3
  size 640856888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784b35e4babb004fdd48c5674cb7a61bed8fb1055006e4a17b61bea8374bcbb
3
  size 640856888