Saiteja commited on
Commit
7c7c85f
1 Parent(s): 63bf9ac

Upload LlamaForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +45 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "philschmid/llama-2-7b-instruction-generator",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "batch_size": 1,
21
+ "bits": 4,
22
+ "block_name_to_quantize": "model.layers",
23
+ "damp_percent": 0.1,
24
+ "dataset": "wikitext2",
25
+ "desc_act": false,
26
+ "disable_exllama": true,
27
+ "group_size": 128,
28
+ "model_seqlen": 4096,
29
+ "module_name_preceding_first_block": [
30
+ "model.embed_tokens"
31
+ ],
32
+ "pad_token_id": null,
33
+ "quant_method": "gptq",
34
+ "sym": true,
35
+ "true_sequential": true,
36
+ "use_cuda_fp16": true
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.32.1",
43
+ "use_cache": true,
44
+ "vocab_size": 32000
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948e640b43ccd64ef50777778d2d06d3b9a6c602783c954ad3d991988170bcf3
3
+ size 3896962836