Hugging Face's logo

nm-testing
/
granite-3.1-8b-instruct2of4-sparse

Safetensors
granite
compressed-tensors
Model card Files
xet
Community
granite-3.1-8b-instruct2of4-sparse
File size: 1,213 Bytes
fd1465f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
{
  "_name_or_path": "ibm-granite/granite-3.1-8b-instruct",
  "architectures": [
    "GraniteForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "attention_multiplier": 0.0078125,
  "bos_token_id": 0,
  "embedding_multiplier": 12.0,
  "eos_token_id": 0,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12800,
  "logits_scaling": 16.0,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "granite",
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "sparsity_config": {
      "format": "dense",
      "global_sparsity": 0.4759316454915897,
      "ignore": [
        "lm_head"
      ],
      "registry_requires_subclass": false,
      "sparsity_structure": "2:4",
      "targets": [
        "Linear"
      ]
    },
    "version": "0.9.1"
  },
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.0",
  "use_cache": true,
  "vocab_size": 49155
}