ivanfioravanti commited on
Commit
d936534
1 Parent(s): 70a000d

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-70b-hf-4bit-MLX
12
+ This model was converted to MLX format from [`codellama/CodeLlama-70b-hf`]().
13
+ Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-70b-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-70b-hf-4bit-MLX")
24
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
25
+ ```
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32016,
3
+ "max_position_embeddings": 16384,
4
+ "hidden_size": 8192,
5
+ "intermediate_size": 28672,
6
+ "num_hidden_layers": 80,
7
+ "num_attention_heads": 64,
8
+ "num_key_value_heads": 8,
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/ifioravanti/.cache/huggingface/hub/models--codellama--CodeLlama-70b-hf/snapshots/4570a4edc524fb9f20f605b417bb43828fa5997a",
80
+ "transformers_version": "4.36.2",
81
+ "model_type": "llama",
82
+ "quantization": {
83
+ "group_size": 64,
84
+ "bits": 4
85
+ }
86
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6405a067d19a80080b0440e1266fdd5f361290596050975537678ec2a763f3
3
+ size 5337867948
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e836ec2fc634d6859caa285abc6be64fc50f1facd64753c6899ce2569349b917
3
+ size 5341836690
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3e6e95ffe05d49193f67958a4ba4679460cf94ba508a6e741835a1797fe85b
3
+ size 5332398774
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0044aa5c41162bebe57f7b9d78b7f6821ca81d26e68ff6003dd801ca62cd66d0
3
+ size 5294649693
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa3f448cd7a2a80af641d7856792665d1b3b6d103d3a4893c2ceb93e6c87178
3
+ size 5294649675
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d34603dae76d0038ee19d99c7f13dfd661266b79e1e305bcf95c12ad6bd28b
3
+ size 5294649647
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905941f8f32731fdc38d42e2656456b1773150adec13e5ae61c34b16d03e5471
3
+ size 5294649703
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f2ac7c9b3b234baf6b2eb37bf394c703bfe73b9040a773b53b11658923035d
3
+ size 1987937565
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
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 sha256:99049b351301fb75b3b0587a484b675cbfd51abe27d2b92eabd385e4c41f97e9
3
+ size 500033
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
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
+ }