skirano commited on
Commit
17e2b10
β€’
1 Parent(s): a9d7a87

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - code
4
+ license: llama2
5
+ tags:
6
+ - llama-2
7
+ - mlx
8
+ pipeline_tag: text-generation
9
+ ---
10
+
11
+ # mlx-community/CodeLlama-7b-Python-4bit
12
+ This model was converted to MLX format from [`codellama/CodeLlama-7b-Python-hf`]().
13
+ Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) 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/CodeLlama-7b-Python-4bit")
24
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
25
+ ```
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "▁<EOT>": 32003,
3
+ "▁<MID>": 32001,
4
+ "▁<PRE>": 32000,
5
+ "▁<SUF>": 32002
6
+ }
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32000,
3
+ "max_position_embeddings": 16384,
4
+ "hidden_size": 4096,
5
+ "intermediate_size": 11008,
6
+ "num_hidden_layers": 32,
7
+ "num_attention_heads": 32,
8
+ "num_key_value_heads": 32,
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": "/Users/skirano/.cache/huggingface/hub/models--codellama--CodeLlama-7b-Python-hf/snapshots/953594314d3f482e2cfc1cf1778a10f994e6896d",
80
+ "transformers_version": "4.36.2",
81
+ "model_type": "llama",
82
+ "quantization": {
83
+ "group_size": 64,
84
+ "bits": 4
85
+ }
86
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "▁<MID>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "▁<SUF>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "eot_token": "▁<EOT>",
72
+ "fill_token": "<FILL_ME>",
73
+ "legacy": null,
74
+ "middle_token": "▁<MID>",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": null,
77
+ "prefix_token": "▁<PRE>",
78
+ "sp_model_kwargs": {},
79
+ "suffix_token": "▁<SUF>",
80
+ "tokenizer_class": "CodeLlamaTokenizer",
81
+ "unk_token": "<unk>",
82
+ "use_default_system_prompt": false
83
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dede4f2e2c6551b1d49b073279daa971ae895f21fd1b33ec2a5919e06b30274e
3
+ size 3979241482