File size: 1,570 Bytes
7ff7c51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "_name_or_path": "/covalent/.cache/models/tmp63r76xg6zltketw4",
    "architectures": [
        "Gemma2ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": 50.0,
    "bos_token_id": 2,
    "cache_implementation": "hybrid",
    "eos_token_id": 1,
    "final_logit_softcapping": 30.0,
    "head_dim": 256,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "model_type": "gemma2",
    "num_attention_heads": 16,
    "num_hidden_layers": 42,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "llm_int8_enable_fp32_cpu_offload": false,
        "llm_int8_has_fp16_weight": false,
        "llm_int8_skip_modules": [
            "lm_head"
        ],
        "llm_int8_threshold": 6.0,
        "load_in_4bit": false,
        "load_in_8bit": true,
        "quant_method": "bitsandbytes"
    },
    "query_pre_attn_scalar": 224,
    "rms_norm_eps": 1e-06,
    "rope_theta": 10000.0,
    "sliding_window": 4096,
    "sliding_window_size": 4096,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 256000,
    "api_key": null
}