File size: 1,369 Bytes
d6f2919
0afe74a
d6f2919
 
 
 
 
 
 
0afe74a
 
d6f2919
 
 
 
 
 
 
 
 
 
 
0afe74a
d6f2919
0afe74a
 
 
d6f2919
0afe74a
 
 
d6f2919
0afe74a
 
 
 
 
d6f2919
 
0afe74a
 
 
 
d6f2919
 
 
 
 
 
0afe74a
d6f2919
0afe74a
d6f2919
 
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
{
  "_name_or_path": "360Zhinao-7B-Chat-4K",
  "architectures": [
    "ZhinaoForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_zhinao.ZhinaoConfig",
    "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM"
  },
  "bf16": false,
  "fp16": true,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.01,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_max_length": 4096,
  "model_type": "zhinao",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "modules_in_block_to_quantize": null,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false,
    "use_exllama": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.38.1",
  "use_cache": false,
  "use_flash_attn": true,
  "vocab_size": 158464
}