Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
File size: 1,064 Bytes
2d084a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "_name_or_path": "/workspace/process/py007_tinyllama-1.1b-chat-v0.3/source",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 5632,
    "max_position_embeddings": 2048,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 22,
    "num_key_value_heads": 4,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.34.0.dev0",
    "use_cache": true,
    "vocab_size": 32003,
    "quantization_config": {
        "bits": 4,
        "group_size": 128,
        "damp_percent": 0.1,
        "desc_act": true,
        "sym": true,
        "true_sequential": true,
        "model_name_or_path": null,
        "model_file_base_name": "model",
        "quant_method": "gptq"
    }
}