Sujan42024 commited on
Commit
25471cd
1 Parent(s): cd162c2

Upload model

Browse files
Files changed (3) hide show
  1. config.json +74 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aisquared/dlite-v2-1_5b",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "custom_pipelines": {
10
+ "text-generation": {
11
+ "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
12
+ "pt": "AutoModelForCausalLM",
13
+ "tf": "TFAutoModelForCausalLM"
14
+ }
15
+ },
16
+ "embd_pdrop": 0.1,
17
+ "eos_token_id": 50256,
18
+ "initializer_range": 0.02,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 1600,
23
+ "n_head": 25,
24
+ "n_inner": null,
25
+ "n_layer": 48,
26
+ "n_positions": 1024,
27
+ "output_past": true,
28
+ "quantization_config": {
29
+ "batch_size": 1,
30
+ "bits": 2,
31
+ "block_name_to_quantize": "transformer.h",
32
+ "cache_block_outputs": true,
33
+ "damp_percent": 0.1,
34
+ "dataset": "c4",
35
+ "desc_act": false,
36
+ "exllama_config": {
37
+ "version": 1
38
+ },
39
+ "group_size": 128,
40
+ "max_input_length": null,
41
+ "model_seqlen": 1024,
42
+ "module_name_preceding_first_block": [
43
+ "transformer.wte",
44
+ "transformer.wpe",
45
+ "transformer.drop"
46
+ ],
47
+ "pad_token_id": null,
48
+ "quant_method": "gptq",
49
+ "sym": true,
50
+ "tokenizer": null,
51
+ "true_sequential": true,
52
+ "use_cuda_fp16": true,
53
+ "use_exllama": true
54
+ },
55
+ "reorder_and_upcast_attn": false,
56
+ "resid_pdrop": 0.1,
57
+ "scale_attn_by_inverse_layer_idx": false,
58
+ "scale_attn_weights": true,
59
+ "summary_activation": null,
60
+ "summary_first_dropout": 0.1,
61
+ "summary_proj_to_labels": true,
62
+ "summary_type": "cls_index",
63
+ "summary_use_proj": true,
64
+ "task_specific_params": {
65
+ "text-generation": {
66
+ "do_sample": true,
67
+ "max_length": 50
68
+ }
69
+ },
70
+ "torch_dtype": "float16",
71
+ "transformers_version": "4.35.2",
72
+ "use_cache": false,
73
+ "vocab_size": 50260
74
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.35.2",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156d81f4041839a439a6bfabd2adef1d849e4cdec63ba13616498a7d217e3772
3
+ size 563634392