Hugging Face's logo

TheBloke
/
llama-30b-supercot-SuperHOT-8K-GPTQ

Text Generation
Transformers
Safetensors
llama
custom_code
text-generation-inference
4-bit precision
gptq
Model card Files Community
1
llama-30b-supercot-SuperHOT-8K-GPTQ
File size: 1,063 Bytes 
8043c14
c748f3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8043c14
 
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/superhot_process/llama-30b-supercot/source",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 6656,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_position_embeddings": 8192,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 52,
  "num_hidden_layers": 60,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.30.0.dev0",
  "use_cache": true,
  "vocab_size": 32000,
  "auto_map": {
    "AutoModel": "modelling_llama.LlamaModel",
    "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
    "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
  },
  "quantization_config": {
    "bits": 4,
    "group_size": -1,
    "damp_percent": 0.01,
    "desc_act": true,
    "sym": true,
    "true_sequential": true,
    "model_file_base_name": "model",
    "quant_method": "gptq"
  }
}