MLX
llama
mc0ps commited on
Commit
f757565
Β·
verified Β·
1 Parent(s): 8443173

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - mlx
5
+ base_model: codellama/CodeLlama-13b-Instruct-hf
6
+ model-index:
7
+ - name: NexusRaven-13B
8
+ results: []
9
+ ---
10
+
11
+ # mlx-community/NexusRaven-V2-13B-4bit-mlx
12
+ This model was converted to MLX format from [`Nexusflow/NexusRaven-V2-13B`]().
13
+ Refer to the [original model card](https://huggingface.co/Nexusflow/NexusRaven-V2-13B) for more details on the model.
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install mlx-lm
18
+ ```
19
+
20
+ ```python
21
+ from mlx_lm import load, generate
22
+
23
+ model, tokenizer = load("mlx-community/NexusRaven-V2-13B-4bit-mlx")
24
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
25
+ ```
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<bot>:": 32017,
3
+ "<bot_end>": 32019,
4
+ "<docstring_end>": 32023,
5
+ "<docstring_start>": 32022,
6
+ "<func_end>": 32021,
7
+ "<func_start>": 32020,
8
+ "<human>:": 32016,
9
+ "<human_end>": 32018
10
+ }
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32024,
3
+ "max_position_embeddings": 16384,
4
+ "hidden_size": 5120,
5
+ "intermediate_size": 13824,
6
+ "num_hidden_layers": 40,
7
+ "num_attention_heads": 40,
8
+ "num_key_value_heads": 40,
9
+ "hidden_act": "silu",
10
+ "initializer_range": 0.02,
11
+ "rms_norm_eps": 1e-05,
12
+ "pretraining_tp": 1,
13
+ "use_cache": true,
14
+ "rope_theta": 1000000,
15
+ "rope_scaling": null,
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "return_dict": true,
19
+ "output_hidden_states": false,
20
+ "output_attentions": false,
21
+ "torchscript": false,
22
+ "torch_dtype": "bfloat16",
23
+ "use_bfloat16": false,
24
+ "tf_legacy_loss": false,
25
+ "pruned_heads": {},
26
+ "tie_word_embeddings": false,
27
+ "is_encoder_decoder": false,
28
+ "is_decoder": false,
29
+ "cross_attention_hidden_size": null,
30
+ "add_cross_attention": false,
31
+ "tie_encoder_decoder": false,
32
+ "max_length": 20,
33
+ "min_length": 0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "num_beams": 1,
37
+ "num_beam_groups": 1,
38
+ "diversity_penalty": 0.0,
39
+ "temperature": 1.0,
40
+ "top_k": 50,
41
+ "top_p": 1.0,
42
+ "typical_p": 1.0,
43
+ "repetition_penalty": 1.0,
44
+ "length_penalty": 1.0,
45
+ "no_repeat_ngram_size": 0,
46
+ "encoder_no_repeat_ngram_size": 0,
47
+ "bad_words_ids": null,
48
+ "num_return_sequences": 1,
49
+ "chunk_size_feed_forward": 0,
50
+ "output_scores": false,
51
+ "return_dict_in_generate": false,
52
+ "forced_bos_token_id": null,
53
+ "forced_eos_token_id": null,
54
+ "remove_invalid_values": false,
55
+ "exponential_decay_length_penalty": null,
56
+ "suppress_tokens": null,
57
+ "begin_suppress_tokens": null,
58
+ "architectures": [
59
+ "LlamaForCausalLM"
60
+ ],
61
+ "finetuning_task": null,
62
+ "id2label": {
63
+ "0": "LABEL_0",
64
+ "1": "LABEL_1"
65
+ },
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1
69
+ },
70
+ "tokenizer_class": null,
71
+ "prefix": null,
72
+ "bos_token_id": 1,
73
+ "pad_token_id": null,
74
+ "eos_token_id": 2,
75
+ "sep_token_id": null,
76
+ "decoder_start_token_id": null,
77
+ "task_specific_params": null,
78
+ "problem_type": null,
79
+ "_name_or_path": "/Volumes/Projects/MLX/cache/models--Nexusflow--NexusRaven-V2-13B/snapshots/d7f2b784d1c3281486077cd81d42d09871128512",
80
+ "transformers_version": "4.36.2",
81
+ "low_cpu_mem_usage": true,
82
+ "model_type": "llama",
83
+ "quantization": {
84
+ "group_size": 64,
85
+ "bits": 4
86
+ }
87
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "<human>:",
8
+ "<bot>:",
9
+ "<human_end>",
10
+ "<bot_end>",
11
+ "<func_start>",
12
+ "<func_end>",
13
+ "<docstring_start>",
14
+ "<docstring_end>",
15
+ "▁<PRE>",
16
+ "▁<MID>",
17
+ "▁<SUF>",
18
+ "▁<EOT>"
19
+ ],
20
+ "bos_token": {
21
+ "content": "<s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "eos_token": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "</s>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "unk_token": {
42
+ "content": "<unk>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ }
48
+ }
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32016": {
62
+ "content": "<human>:",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32017": {
70
+ "content": "<bot>:",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32018": {
78
+ "content": "<human_end>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32019": {
86
+ "content": "<bot_end>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32020": {
94
+ "content": "<func_start>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32021": {
102
+ "content": "<func_end>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32022": {
110
+ "content": "<docstring_start>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32023": {
118
+ "content": "<docstring_end>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ }
125
+ },
126
+ "additional_special_tokens": [
127
+ "▁<PRE>",
128
+ "▁<MID>",
129
+ "▁<SUF>",
130
+ "▁<EOT>",
131
+ "<human>:",
132
+ "<bot>:",
133
+ "<human_end>",
134
+ "<bot_end>",
135
+ "<func_start>",
136
+ "<func_end>",
137
+ "<docstring_start>",
138
+ "<docstring_end>",
139
+ "▁<PRE>",
140
+ "▁<MID>",
141
+ "▁<SUF>",
142
+ "▁<EOT>"
143
+ ],
144
+ "bos_token": "<s>",
145
+ "clean_up_tokenization_spaces": false,
146
+ "eos_token": "</s>",
147
+ "eot_token": "▁<EOT>",
148
+ "fill_token": "<FILL_ME>",
149
+ "legacy": null,
150
+ "middle_token": "▁<MID>",
151
+ "model_max_length": 8192,
152
+ "pad_token": "</s>",
153
+ "prefix_token": "▁<PRE>",
154
+ "sp_model_kwargs": {},
155
+ "suffix_token": "▁<SUF>",
156
+ "tokenizer_class": "CodeLlamaTokenizer",
157
+ "truncation_side": "left",
158
+ "unk_token": "<unk>",
159
+ "use_default_system_prompt": false
160
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c4059ff69d88e5d32c9afa6ac59fb377e9ddbfd54f02fdcfe4f255a1ec72a9
3
+ size 7793656443