Felladrin commited on
Commit
8ff2de7
·
1 Parent(s): 62109c2

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - text-generation
7
+ - mlx
8
+ datasets:
9
+ - ehartford/wizard_vicuna_70k_unfiltered
10
+ - totally-not-an-llm/EverythingLM-data-V3
11
+ - Open-Orca/SlimOrca-Dedup
12
+ - databricks/databricks-dolly-15k
13
+ - THUDM/webglm-qa
14
+ base_model: JackFram/llama-160m
15
+ widget:
16
+ - text: '<|im_start|>system
17
+
18
+ You are a helpful assistant, who answers with empathy.<|im_end|>
19
+
20
+ <|im_start|>user
21
+
22
+ Got a question for you!<|im_end|>
23
+
24
+ <|im_start|>assistant
25
+
26
+ Sure! What''s it?<|im_end|>
27
+
28
+ <|im_start|>user
29
+
30
+ Why do you love cats so much!? 🐈<|im_end|>
31
+
32
+ <|im_start|>assistant'
33
+ - text: '<|im_start|>system
34
+
35
+ You are a helpful assistant who answers user''s questions with empathy.<|im_end|>
36
+
37
+ <|im_start|>user
38
+
39
+ Who is Mona Lisa?<|im_end|>
40
+
41
+ <|im_start|>assistant'
42
+ - text: '<|im_start|>system
43
+
44
+ You are a helpful assistant who provides concise responses.<|im_end|>
45
+
46
+ <|im_start|>user
47
+
48
+ Heya!<|im_end|>
49
+
50
+ <|im_start|>assistant
51
+
52
+ Hi! How may I help you today?<|im_end|>
53
+
54
+ <|im_start|>user
55
+
56
+ I need to build a simple website. Where should I start learning about web development?<|im_end|>
57
+
58
+ <|im_start|>assistant'
59
+ - text: '<|im_start|>user
60
+
61
+ Invited some friends to come home today. Give me some ideas for games to play
62
+ with them!<|im_end|>
63
+
64
+ <|im_start|>assistant'
65
+ - text: '<|im_start|>system
66
+
67
+ You are a helpful assistant who answers user''s questions with details and curiosity.<|im_end|>
68
+
69
+ <|im_start|>user
70
+
71
+ What are some potential applications for quantum computing?<|im_end|>
72
+
73
+ <|im_start|>assistant'
74
+ - text: '<|im_start|>system
75
+
76
+ You are a helpful assistant who gives creative responses.<|im_end|>
77
+
78
+ <|im_start|>user
79
+
80
+ Write the specs of a game about mages in a fantasy world.<|im_end|>
81
+
82
+ <|im_start|>assistant'
83
+ - text: '<|im_start|>system
84
+
85
+ You are a helpful assistant who answers user''s questions with details.<|im_end|>
86
+
87
+ <|im_start|>user
88
+
89
+ Tell me about the pros and cons of social media.<|im_end|>
90
+
91
+ <|im_start|>assistant'
92
+ - text: '<|im_start|>system
93
+
94
+ You are a helpful assistant who answers user''s questions with confidence.<|im_end|>
95
+
96
+ <|im_start|>user
97
+
98
+ What is a dog?<|im_end|>
99
+
100
+ <|im_start|>assistant
101
+
102
+ A dog is a four-legged, domesticated animal that is a member of the class Mammalia,
103
+ which includes all mammals. Dogs are known for their loyalty, playfulness, and
104
+ ability to be trained for various tasks. They are also used for hunting, herding,
105
+ and as service animals.<|im_end|>
106
+
107
+ <|im_start|>user
108
+
109
+ What is the color of an apple?<|im_end|>
110
+
111
+ <|im_start|>assistant'
112
+ inference:
113
+ parameters:
114
+ max_new_tokens: 250
115
+ penalty_alpha: 0.5
116
+ top_k: 4
117
+ repetition_penalty: 1.01
118
+ ---
119
+
120
+ # Llama-160M-Chat-v1-4bit-mlx
121
+ This model was converted to MLX format from [`Felladrin/Llama-160M-Chat-v1`]().
122
+ Refer to the [original model card](https://huggingface.co/Felladrin/Llama-160M-Chat-v1) for more details on the model.
123
+ ## Use with mlx
124
+ ```bash
125
+ pip install mlx
126
+ git clone https://github.com/ml-explore/mlx-examples.git
127
+ cd mlx-examples/llms/hf_llm
128
+ python generate.py --model mlx-community/Llama-160M-Chat-v1-4bit-mlx --prompt "My name is"
129
+ ```
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32000,
3
+ "max_position_embeddings": 2048,
4
+ "hidden_size": 768,
5
+ "intermediate_size": 3072,
6
+ "num_hidden_layers": 12,
7
+ "num_attention_heads": 12,
8
+ "num_key_value_heads": 12,
9
+ "hidden_act": "silu",
10
+ "initializer_range": 0.02,
11
+ "rms_norm_eps": 1e-06,
12
+ "pretraining_tp": 1,
13
+ "use_cache": true,
14
+ "rope_theta": 10000.0,
15
+ "rope_scaling": null,
16
+ "attention_bias": false,
17
+ "return_dict": true,
18
+ "output_hidden_states": false,
19
+ "output_attentions": false,
20
+ "torchscript": false,
21
+ "torch_dtype": "float32",
22
+ "use_bfloat16": false,
23
+ "tf_legacy_loss": false,
24
+ "pruned_heads": {},
25
+ "tie_word_embeddings": false,
26
+ "is_encoder_decoder": false,
27
+ "is_decoder": false,
28
+ "cross_attention_hidden_size": null,
29
+ "add_cross_attention": false,
30
+ "tie_encoder_decoder": false,
31
+ "max_length": 20,
32
+ "min_length": 0,
33
+ "do_sample": false,
34
+ "early_stopping": false,
35
+ "num_beams": 1,
36
+ "num_beam_groups": 1,
37
+ "diversity_penalty": 0.0,
38
+ "temperature": 1.0,
39
+ "top_k": 50,
40
+ "top_p": 1.0,
41
+ "typical_p": 1.0,
42
+ "repetition_penalty": 1.0,
43
+ "length_penalty": 1.0,
44
+ "no_repeat_ngram_size": 0,
45
+ "encoder_no_repeat_ngram_size": 0,
46
+ "bad_words_ids": null,
47
+ "num_return_sequences": 1,
48
+ "chunk_size_feed_forward": 0,
49
+ "output_scores": false,
50
+ "return_dict_in_generate": false,
51
+ "forced_bos_token_id": null,
52
+ "forced_eos_token_id": null,
53
+ "remove_invalid_values": false,
54
+ "exponential_decay_length_penalty": null,
55
+ "suppress_tokens": null,
56
+ "begin_suppress_tokens": null,
57
+ "architectures": [
58
+ "LlamaForCausalLM"
59
+ ],
60
+ "finetuning_task": null,
61
+ "id2label": {
62
+ "0": "LABEL_0",
63
+ "1": "LABEL_1"
64
+ },
65
+ "label2id": {
66
+ "LABEL_0": 0,
67
+ "LABEL_1": 1
68
+ },
69
+ "tokenizer_class": null,
70
+ "prefix": null,
71
+ "bos_token_id": 1,
72
+ "pad_token_id": 0,
73
+ "eos_token_id": 2,
74
+ "sep_token_id": null,
75
+ "decoder_start_token_id": null,
76
+ "task_specific_params": null,
77
+ "problem_type": null,
78
+ "_name_or_path": "Felladrin/Llama-160M-Chat-v1",
79
+ "transformers_version": "4.35.2",
80
+ "model_type": "llama",
81
+ "quantization": {
82
+ "group_size": 64,
83
+ "bits": 4
84
+ }
85
+ }
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a0a8dd2483a1e6b13cdaf6aaf7d0cb52556f461132a6d35a0c8425a293c199
3
+ size 126745598