DaertML commited on
Commit
3c3e219
·
1 Parent(s): cc13f34

Add quantized 4 bit version of the model

Browse files
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./tinystarcoder",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 768,
20
+ "n_head": 12,
21
+ "n_inner": 3072,
22
+ "n_layer": 20,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "quantization_config": {
27
+ "batch_size": 1,
28
+ "bits": 4,
29
+ "block_name_to_quantize": "transformer.h",
30
+ "damp_percent": 0.1,
31
+ "dataset": "wikitext2",
32
+ "desc_act": false,
33
+ "disable_exllama": false,
34
+ "group_size": 128,
35
+ "model_seqlen": 8192,
36
+ "module_name_preceding_first_block": [
37
+ "transformer.wte",
38
+ "transformer.wpe",
39
+ "transformer.drop"
40
+ ],
41
+ "pad_token_id": null,
42
+ "quant_method": "gptq",
43
+ "sym": true,
44
+ "tokenizer": null,
45
+ "true_sequential": true,
46
+ "use_cuda_fp16": true
47
+ },
48
+ "resid_pdrop": 0.1,
49
+ "scale_attention_softmax_in_fp32": true,
50
+ "scale_attn_weights": true,
51
+ "summary_activation": null,
52
+ "summary_first_dropout": 0.1,
53
+ "summary_proj_to_labels": true,
54
+ "summary_type": "cls_index",
55
+ "summary_use_proj": true,
56
+ "torch_dtype": "float16",
57
+ "transformers_version": "4.33.1",
58
+ "use_cache": true,
59
+ "validate_runner_input": true,
60
+ "vocab_size": 49152
61
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.33.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ab684ed8d87ea182423c45c6e2e3e2972a184801ca7ec05ff67b5c687bff43
3
+ size 151323101
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": "<|endoftext|>",
24
+ "eos_token": "<|endoftext|>",
25
+ "unk_token": "<|endoftext|>"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "additional_special_tokens": [
4
+ "<|endoftext|>",
5
+ "<fim_prefix>",
6
+ "<fim_middle>",
7
+ "<fim_suffix>",
8
+ "<fim_pad>",
9
+ "<filename>",
10
+ "<gh_stars>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<empty_output>",
19
+ "<commit_before>",
20
+ "<commit_msg>",
21
+ "<commit_after>",
22
+ "<reponame>"
23
+ ],
24
+ "bos_token": "<|endoftext|>",
25
+ "clean_up_tokenization_spaces": true,
26
+ "eos_token": "<|endoftext|>",
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "<|endoftext|>",
30
+ "vocab_size": 49152
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff