File size: 2,365 Bytes
be16c82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39eede4
e318c1f
39eede4
 
be16c82
 
e318c1f
 
be16c82
 
39eede4
 
 
be16c82
 
 
39eede4
be16c82
 
 
 
e318c1f
39eede4
e318c1f
 
 
 
 
be16c82
 
 
39eede4
be16c82
 
 
 
 
 
 
 
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
87
88
89
{
  "version": "0.1.0",
  "model_type": "gemma2",
  "quantization": "q4f16_1",
  "model_config": {
    "hidden_size": 2304,
    "intermediate_size": 9216,
    "attention_bias": false,
    "num_attention_heads": 8,
    "num_key_value_heads": 4,
    "head_dim": 256,
    "num_hidden_layers": 26,
    "rms_norm_eps": 1e-06,
    "vocab_size": 256002,
    "hidden_activation": "gelu_pytorch_tanh",
    "position_embedding_base": 10000.0,
    "context_window_size": 4096,
    "prefill_chunk_size": 2048,
    "tensor_parallel_shards": 1,
    "max_batch_size": 80,
    "attn_logit_softcapping": 50.0,
    "final_logit_softcapping": 30.0,
    "query_pre_attn_scalar": 256,
    "sliding_window": 4096
  },
  "vocab_size": 256002,
  "context_window_size": 4096,
  "sliding_window_size": -1,
  "prefill_chunk_size": 2048,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "pipeline_parallel_stages": 1,
  "temperature": 1.0,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "repetition_penalty": 1.0,
  "top_p": 1.0,
  "tokenizer_files": [
    "tokenizer.model",
    "tokenizer.json",
    "added_tokens.json",
    "tokenizer_config.json"
  ],
  "tokenizer_info": {
    "token_postproc_method": "byte_fallback",
    "prepend_space_in_encode": false,
    "strip_space_in_decode": false
  },
  "conv_template": {
    "name": "chatml",
    "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
    "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
    "system_prefix_token_ids": null,
    "add_role_after_system_message": true,
    "roles": {
      "user": "<|im_start|>user",
      "assistant": "<|im_start|>assistant"
    },
    "role_templates": {
      "user": "{user_message}",
      "assistant": "{assistant_message}",
      "tool": "{tool_message}"
    },
    "messages": [],
    "seps": [
      "<|im_end|>\n"
    ],
    "role_content_sep": "\n",
    "role_empty_sep": "\n",
    "stop_str": [
      "<|im_end|>",
      "<end_of_turn>",
      "<|im_start|>",
      "<|start_header_id|>",
      "<|end_header_id|>",
      "<|eot_id|>",
      "<start_of_turn>",
      "<end_of_turn>"
    ],
    "stop_token_ids": [
      2
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 0,
  "bos_token_id": 2,
  "eos_token_id": 1
}