mzbac commited on
Commit
7ac55fb
·
1 Parent(s): 6de4ffb

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - mlx
5
+ license_name: yi-license
6
+ license_link: LICENSE
7
+ widget:
8
+ - example_title: Yi-34B-Chat
9
+ text: hi
10
+ output:
11
+ text: ' Hello! How can I assist you today?'
12
+ - example_title: Yi-34B
13
+ text: There's a place where time stands still. A place of breath taking wonder,
14
+ but also
15
+ output:
16
+ text: ' an eerie sense that something is just not right…
17
+
18
+ Between the two worlds lies The Forgotten Kingdom - home to creatures long since
19
+ thought extinct and ancient magic so strong it defies belief! Only here can
20
+ you find what has been lost for centuries: An Elixir Of Life which will restore
21
+ youth and vitality if only those who seek its power are brave enough to face
22
+ up against all manner of dangers lurking in this mysterious land! But beware;
23
+ some say there may even exist powerful entities beyond our comprehension whose
24
+ intentions towards humanity remain unclear at best ---- they might want nothing
25
+ more than destruction itself rather then anything else from their quest after
26
+ immortality (and maybe someone should tell them about modern medicine)? In any
27
+ event though – one thing remains true regardless : whether or not success comes
28
+ easy depends entirely upon how much effort we put into conquering whatever challenges
29
+ lie ahead along with having faith deep down inside ourselves too ;) So let’s
30
+ get started now shall We?'
31
+ pipeline_tag: text-generation
32
+ ---
33
+
34
+ # Yi-34B-Chat-hf-4bit-mlx
35
+ This model was converted to MLX format from [`01-ai/Yi-34B-Chat`]().
36
+ Refer to the [original model card](https://huggingface.co/01-ai/Yi-34B-Chat) for more details on the model.
37
+ ## Use with mlx
38
+ ```bash
39
+ pip install mlx
40
+ git clone https://github.com/ml-explore/mlx-examples.git
41
+ cd mlx-examples/llms/hf_llm
42
+ python generate.py --model mlx-community/Yi-34B-Chat-hf-4bit-mlx --prompt "My name is"
43
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 64001,
3
+ "<|startoftext|>": 64000
4
+ }
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32256,
3
+ "max_position_embeddings": 16384,
4
+ "hidden_size": 7168,
5
+ "intermediate_size": 19200,
6
+ "num_hidden_layers": 62,
7
+ "num_attention_heads": 56,
8
+ "num_key_value_heads": 8,
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": 100000,
15
+ "rope_scaling": {
16
+ "factor": 4.0,
17
+ "type": "linear"
18
+ },
19
+ "attention_bias": false,
20
+ "attention_dropout": 0.0,
21
+ "return_dict": true,
22
+ "output_hidden_states": false,
23
+ "output_attentions": false,
24
+ "torchscript": false,
25
+ "torch_dtype": "bfloat16",
26
+ "use_bfloat16": false,
27
+ "tf_legacy_loss": false,
28
+ "pruned_heads": {},
29
+ "tie_word_embeddings": false,
30
+ "is_encoder_decoder": false,
31
+ "is_decoder": false,
32
+ "cross_attention_hidden_size": null,
33
+ "add_cross_attention": false,
34
+ "tie_encoder_decoder": false,
35
+ "max_length": 20,
36
+ "min_length": 0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "num_beams": 1,
40
+ "num_beam_groups": 1,
41
+ "diversity_penalty": 0.0,
42
+ "temperature": 1.0,
43
+ "top_k": 50,
44
+ "top_p": 1.0,
45
+ "typical_p": 1.0,
46
+ "repetition_penalty": 1.0,
47
+ "length_penalty": 1.0,
48
+ "no_repeat_ngram_size": 0,
49
+ "encoder_no_repeat_ngram_size": 0,
50
+ "bad_words_ids": null,
51
+ "num_return_sequences": 1,
52
+ "chunk_size_feed_forward": 0,
53
+ "output_scores": false,
54
+ "return_dict_in_generate": false,
55
+ "forced_bos_token_id": null,
56
+ "forced_eos_token_id": null,
57
+ "remove_invalid_values": false,
58
+ "exponential_decay_length_penalty": null,
59
+ "suppress_tokens": null,
60
+ "begin_suppress_tokens": null,
61
+ "architectures": [
62
+ "LlamaForCausalLM"
63
+ ],
64
+ "finetuning_task": null,
65
+ "id2label": {
66
+ "0": "LABEL_0",
67
+ "1": "LABEL_1"
68
+ },
69
+ "label2id": {
70
+ "LABEL_0": 0,
71
+ "LABEL_1": 1
72
+ },
73
+ "tokenizer_class": null,
74
+ "prefix": null,
75
+ "bos_token_id": 32013,
76
+ "pad_token_id": null,
77
+ "eos_token_id": 32021,
78
+ "sep_token_id": null,
79
+ "decoder_start_token_id": null,
80
+ "task_specific_params": null,
81
+ "problem_type": null,
82
+ "_name_or_path": "./deepseek-ai/deepseek-coder-33b-instruct",
83
+ "transformers_version": "4.36.2",
84
+ "model_type": "llama",
85
+ "quantization": {
86
+ "group_size": 64,
87
+ "bits": 4
88
+ }
89
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|EOT|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "32000": {
6
+ "content": "õ",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "32001": {
14
+ "content": "÷",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "32002": {
22
+ "content": "Á",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32003": {
30
+ "content": "ý",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32004": {
38
+ "content": "À",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32006": {
54
+ "content": "ø",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32007": {
62
+ "content": "ú",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32008": {
70
+ "content": "þ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32009": {
78
+ "content": "ü",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32010": {
86
+ "content": "ù",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32011": {
94
+ "content": "ö",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32012": {
102
+ "content": "û",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32013": {
110
+ "content": "<|begin▁of▁sentence|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32014": {
118
+ "content": "<|end▁of▁sentence|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32015": {
126
+ "content": "<|fim▁hole|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32016": {
134
+ "content": "<|fim▁begin|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32017": {
142
+ "content": "<|fim▁end|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32018": {
150
+ "content": "<pad>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32019": {
158
+ "content": "<|User|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32020": {
166
+ "content": "<|Assistant|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32021": {
174
+ "content": "<|EOT|>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "additional_special_tokens": [],
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
185
+ "clean_up_tokenization_spaces": false,
186
+ "eos_token": "<|EOT|>",
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<|end▁of▁sentence|>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": true
194
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de268fa722800954bf758916a81773e96772b48aa4b949e25901e0121195363
3
+ size 16041893953
weights.01.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495cd7e64f9c90031d4c49f9462e2e9171df7b1ad591ab36c59a0ef98f5bc160
3
+ size 3047357114