Felladrin commited on
Commit
f657fe6
0 Parent(s):

Initial commit

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - text-generation
7
+ base_model: JackFram/llama-68m
8
+ datasets:
9
+ - THUDM/webglm-qa
10
+ - databricks/databricks-dolly-15k
11
+ - cognitivecomputations/wizard_vicuna_70k_unfiltered
12
+ - totally-not-an-llm/EverythingLM-data-V3
13
+ - Amod/mental_health_counseling_conversations
14
+ - sablo/oasst2_curated
15
+ - starfishmedical/webGPT_x_dolly
16
+ - Open-Orca/OpenOrca
17
+ - mlabonne/chatml_dpo_pairs
18
+ widget:
19
+ - text: |-
20
+ <|im_start|>system
21
+ You are a knowledgeable assistant. Help the user as much as you can.<|im_end|>
22
+ <|im_start|>user
23
+ How to become healthier?<|im_end|>
24
+ <|im_start|>assistant
25
+ - text: |-
26
+ <|im_start|>system
27
+ You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.<|im_end|>
28
+ <|im_start|>user
29
+ Heya!<|im_end|>
30
+ <|im_start|>assistant
31
+ Hi! How may I help you?<|im_end|>
32
+ <|im_start|>user
33
+ I am interested in developing a career in software engineering. What would you recommend me to do?<|im_end|>
34
+ <|im_start|>assistant
35
+ - text: |-
36
+ <|im_start|>user
37
+ Hey! Got a question for you!<|im_end|>
38
+ <|im_start|>assistant
39
+ Sure! What's it?<|im_end|>
40
+ <|im_start|>user
41
+ I'm planning to travel to the Bahamas! Can you give me some tips?<|im_end|>
42
+ <|im_start|>assistant
43
+ - text: |-
44
+ <|im_start|>system
45
+ You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.<|im_end|>
46
+ <|im_start|>user
47
+ Write the background story of an RPG game about wizards and dragons in a sci-fi world.<|im_end|>
48
+ <|im_start|>assistant
49
+ inference:
50
+ parameters:
51
+ max_new_tokens: 64
52
+ penalty_alpha: 0.5
53
+ top_k: 4
54
+ ---
55
+
56
+ # A Llama Chat Model of 68M Parameters
57
+
58
+ - Base model: [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m)
59
+ - Datasets:
60
+ - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
61
+ - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
62
+ - [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered)
63
+ - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3)
64
+ - [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations)
65
+ - [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated)
66
+ - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly)
67
+ - [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)
68
+ - [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs)
69
+ - Availability in other ML formats:
70
+ - ONNX: [Felladrin/onnx-Llama-68M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-68M-Chat-v1)
71
+
72
+ ## Recommended Prompt Format
73
+
74
+ ```
75
+ <|im_start|>system
76
+ {system_message}<|im_end|>
77
+ <|im_start|>user
78
+ {user_message}<|im_end|>
79
+ <|im_start|>assistant
80
+ ```
81
+
82
+ ## Recommended Inference Parameters
83
+
84
+ ```yml
85
+ penalty_alpha: 0.5
86
+ top_k: 4
87
+ ```
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": ["LlamaForCausalLM"],
3
+ "attention_bias": false,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "hidden_act": "silu",
7
+ "hidden_size": 768,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 3072,
10
+ "max_position_embeddings": 2048,
11
+ "model_type": "llama",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 2,
14
+ "num_key_value_heads": 12,
15
+ "pretraining_tp": 1,
16
+ "rms_norm_eps": 1e-6,
17
+ "rope_scaling": null,
18
+ "rope_theta": 10000.0,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.35.2",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bf4d8d47e9d27cd68543726e6e6192fbc7a2ed061f9d1c3a6cc2a5c452ffbc
3
+ size 272123144
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }