Text Generation
Transformers
Safetensors
5 languages
RefinedWeb
falcon-40b
long-context
falcon
NTK-YaRN
custom_code
text-generation-inference
4-bit precision
awq
File size: 1,056 Bytes
a99ad1e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "_name_or_path": "/workspace/process/lightonai_alfred-40b-1023/source",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "RWForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_RW.RWConfig",
    "AutoModelForCausalLM": "modeling_RW.RWForCausalLM"
  },
  "bias": false,
  "bos_token_id": 11,
  "embedding_scaling_factor": 4,
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "RefinedWeb",
  "multi_query": true,
  "n_head": 128,
  "n_head_kv": 8,
  "n_layer": 60,
  "ntk_scaling_factor": 5,
  "pad_token_id": 0,
  "parallel_attn": true,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "single_ln": false,
  "torch_dtype": "float16",
  "transformers_version": "4.35.0",
  "use_cache": true,
  "vanilla_scaling_factor": null,
  "vocab_size": 65024
}