GusPuffy commited on
Commit
4df1d66
1 Parent(s): 61f0e10

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ model_name: MythoMax L2 13B
6
+ base_model: Gryphe/MythoMax-L2-13b
7
+ inference: false
8
+ model_creator: Gryphe
9
+ model_type: llama
10
+ prompt_template: '```
11
+
12
+ {system_message}
13
+
14
+
15
+ ### Instruction:
16
+
17
+ {prompt}
18
+
19
+ (For roleplay purposes, I suggest the following - Write <CHAR NAME>''s next reply
20
+ in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.)
21
+
22
+
23
+ ### Response:
24
+
25
+
26
+ ```
27
+
28
+ '
29
+ quantized_by: GusPuffy
30
+ ---
31
+
32
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">Part of work associated with <a href="https://www.sentientsimulations.com/">sentientsimulations.com</a></p></div>
33
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
34
+
35
+ # MythoMax L2 13B - AWQ
36
+ - Model creator: [Gryphe](https://huggingface.co/Gryphe)
37
+ - Original model: [MythoMax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b)
38
+
39
+ ## Description
40
+
41
+ This repo contains SqueezeLLM model files for [Gryphe's MythoMax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b).
42
+
43
+
44
+ ### About SqueezeLLM
45
+
46
+ https://github.com/SqueezeAILab/SqueezeLLM
47
+
48
+ Quantized using the steps here: https://github.com/SqueezeAILab/SqueezeLLM/tree/main/quantization
49
+
50
+ ---
51
+ license: other
52
+ ---
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mythomax-L2-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000,
26
+ "quantization_config": {
27
+ "model_name_or_path": null,
28
+ "model_file_base_name": "sq-mythomax-13b-w4-s0",
29
+ "quant_method": "squeezellm"
30
+ }
31
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.32.0.dev0"
10
+ }
quant_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "w_bit": 4
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
sq-mythomax-13b-w4-s0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2b7c66ed008e3ecbcba4cc7de8c42cea699e53716db1666cf2691bb90ae0b7
3
+ size 7792837957
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }