Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-compressed-tensors-kv-cache-scheme

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
TinyLlama-1.1B-compressed-tensors-kv-cache-scheme
File size: 2,163 Bytes 
94914e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
 
{
  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "compression_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "channel",
          "symmetric": true,
          "type": "int"
        }
      },
      "kv_cache": {
        "input_activations": null,
        "output_activations": {
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        },
        "targets": [
          "re:.*k_proj",
          "re:.*v_proj"
        ],
        "weights": null
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [],
    "kv_cache_scheme": {
      "block_structure": null,
      "dynamic": false,
      "group_size": null,
      "num_bits": 8,
      "observer": "minmax",
      "observer_kwargs": {},
      "strategy": "tensor",
      "symmetric": true,
      "type": "float"
    },
    "quant_method": "compressed-tensors",
    "quantization_status": "calibration"
  },
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.42.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}