Upload folder using huggingface_hub

#1
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - fr
5
+ - de
6
+ - es
7
+ - it
8
+ - pt
9
+ - zh
10
+ - ja
11
+ - ru
12
+ - ko
13
+ license: other
14
+ tags:
15
+ - mlx
16
+ license_name: mrl
17
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
18
+ extra_gated_description: If you want to learn more about how we process your personal
19
+ data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
20
+ ---
21
+
22
+ # mlx-community/Mistral-Large-Instruct-2407-4bit
23
+
24
+ The Model [mlx-community/Mistral-Large-Instruct-2407-4bit](https://huggingface.co/mlx-community/Mistral-Large-Instruct-2407-4bit) was converted to MLX format from [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407) using mlx-lm version **0.16.1**.
25
+
26
+ ## Use with mlx
27
+
28
+ ```bash
29
+ pip install mlx-lm
30
+ ```
31
+
32
+ ```python
33
+ from mlx_lm import load, generate
34
+
35
+ model, tokenizer = load("mlx-community/Mistral-Large-Instruct-2407-4bit")
36
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
37
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 12288,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 28672,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 96,
15
+ "num_hidden_layers": 88,
16
+ "num_key_value_heads": 8,
17
+ "quantization": {
18
+ "group_size": 64,
19
+ "bits": 4
20
+ },
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "vocab_size": 32768
29
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a2ca3b4704cd052e1ff2e51debaf2c1e8152c65bf8f4cd6c76c1c937532a48
3
+ size 5280417162
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8682119076809870897a2f19e2521f0f4f8286cb56e329b412b18f984d7b12
3
+ size 5252155094
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae72c583260c6994e799fff83973c096a88eedaaa72822793221826a6eeb6df0
3
+ size 5365401350
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa62c510112093c6a95db568b2506220dc0de5da85162f891f681e282f467bd
3
+ size 5351244918
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed987234622b145c3363b65da174b21b5fdac6c3f9e603c399c17025951a46c2
3
+ size 5252105792
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d241878e33e1451d465f91652210a3713f221754bdb22c91e6e228d8f4363441
3
+ size 5252155193
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252e43cb13a1451380ee8a0314e0e37df435d75c70acc56e1cc202caf6ca3615
3
+ size 5252155185
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0091033c2d48b2febeefb3ddcc86e913d4c6f94dc121e52304d06b6c6f95d77e
3
+ size 5365401388
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2e2865f0e5ddf526b86317e996c55b2a57b2b99febf1a8aa443e99eefc7a19
3
+ size 5351244930
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d7d7193be28007579409dcf123c605a33c7dc02e5fe7349a5e8d9a9a141b69
3
+ size 5252105824
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0014cf77c2effc79f2ad43f0580effb2083e2315efcfe8a024d87765be329d
3
+ size 5252155169
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad725bb51c8122e498d68b5a04bacc7dc66cf0f22876916d2a47515c65e76a8
3
+ size 5252155163
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1ce4cd8ce45ebc1c92701a1bed4a93f2e03853a763a2692f0fbd184d330a88
3
+ size 5266334543
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198cbecacff88979c85cd838d22ff087a5ec71274b839ac28be808e9ff58934e
3
+ size 226492716
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
test.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import json
2
+ from typing import Dict
3
+
4
+ from safetensors.torch import load_file, save_file
5
+ from huggingface_hub import split_torch_state_dict_into_shards
6
+ import torch
7
+ import os
8
+
9
+ def save_state_dict(state_dict: Dict[str, torch.Tensor], save_directory: str):
10
+ state_dict_split = split_torch_state_dict_into_shards(state_dict, filename_pattern='consolidated{suffix}.safetensors')
11
+ for filename, tensors in state_dict_split.filename_to_tensors.items():
12
+ shard = {tensor: state_dict[tensor] for tensor in tensors}
13
+ print("Saving", save_directory, filename)
14
+ save_file(shard, os.path.join(save_directory, filename))
15
+ if state_dict_split.is_sharded:
16
+ index = {
17
+ "metadata": state_dict_split.metadata,
18
+ "weight_map": state_dict_split.tensor_to_filename,
19
+ }
20
+ with open(os.path.join(save_directory, "consolidated.safetensors.index.json"), "w") as f:
21
+ f.write(json.dumps(index, indent=2))
22
+
23
+ big_file = 'consolidated.safetensors'
24
+ loaded = load_file(big_file)
25
+
26
+ save_state_dict(loaded, save_directory=f'.')
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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff