Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- zh
+- ja
+- ru
+- ko
+license: other
+tags:
+- mlx
+license_name: mrl
+license_link: https://mistral.ai/licenses/MRL-0.1.md
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+---
+
+# mlx-community/Mistral-Large-Instruct-2407-8bit
+
+The Model [mlx-community/Mistral-Large-Instruct-2407-8bit](https://huggingface.co/mlx-community/Mistral-Large-Instruct-2407-8bit) 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**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Mistral-Large-Instruct-2407-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,29 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.42.3",
+    "use_cache": true,
+    "vocab_size": 32768
+}

model-00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fe80a964463f8a02a8641548c87643ae2f33564588bea016c0c4910ce7a332
+size 5187462533

model-00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212f1a67d0aa719bdc6ad95d2ca8fd21fc17d17eb7d9606b4c91af8f9b32990b
+size 5160722815

model-00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3dd7adb3282aac8a7fd9142370e294875e2f267d79cbf8904f2a7434cb501b
+size 5134034558

model-00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e70aa9834c8b05c6b3a04ef0244747c44c0a0f7577b27f5a828f69acc43550e
+size 5160722860

model-00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600c328fc983a3a8b084e6df3a7198d2a86ff58b3683a376b1a8ae77e475aac6
+size 5134034644

model-00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ea330c2ec9d1151af7c539e35c3ce0e9bd03374a1c86a87b3f4c1253f5df74
+size 5160722866

model-00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d36ca0c9b623d1398bf3ec3d7b37458f01c5b0676a9de9146ed92335f4d82c4
+size 5134034640

model-00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c0fe00f95deb023562c3028a2f415479bb93cddca4b8ee133976c2cf4a84c0
+size 5160722906

model-00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e33d1495bb4b3ad5d2a8bd050dffb28e592e45371c303e9df6a200b74e429f
+size 5134034638

model-00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a398aad235943301b1d106d2881505933cac1dcb1777aef59343b0886cb7a8a5
+size 5160722878

model-00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f52b27f556784be77ce6cc5905e105138e7ad58bd49baaa10df9046dcfd786b
+size 5134034640

model-00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324fecc8cdc9772a41b87ada2e1a88fe657856e805d53e45097361b711643a7e
+size 5160722870

model-00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f87ce77a0ea4a26207dd28773fc4c89213f61681d717237910c27e6acd3575
+size 5134034648

model-00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2d8392ec985065ec5774d6a3635248e6d7439f295c3e30a21a5e612804227a
+size 5160722894

model-00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f6ee2e8d9c6618e175397fb3a25dbc012e984a4200b9481c0e362074320eca
+size 5134034634

model-00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21de6179d856784fbe1088781894b6df4a0c1dc97b75ee0954de844b7cd9d79b
+size 5160722894

model-00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24eb5a55d9edefa16741a0817a7645ac7e501d0fae327bfc913e61b7502a3dc
+size 5134034640

model-00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f866eb38f96b8fc7017856d9854ef09dea2c9ed333bc6be2c1ac9edcb97dbca8
+size 5160722886

model-00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c20323c1fd999b838ceb1bf96d5d28ee8d6c5cf1b637c74e59751fdc27251ef
+size 5134034642

model-00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0280930e90bf0eef519208ce9b0e3f50c7f6e34a394b187c95f1fc88ce3022b
+size 5160722886

model-00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88921c970a349956a02c8ead0532c1938fb5260d9d170bd7bf8d3197a086ad7
+size 5134034648

model-00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae3bd64e4e38985d40c52dfa2cc49d724647d931fec27c8f56448b23723a0a6
+size 5160722902

model-00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f32f9486306cf10b3b3ec37b0d4f06f73a2258054b4bc102073bccc8ed55417
+size 5134034658

model-00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd7b6e834301b8ed493493582fcf07a8b30a03d2d118bc12aa14d6b09fdaaa5
+size 5160722906

model-00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35752200c588ac4cc0049fee1697eca85f9876215fdd2aabbd3814da6d66766a
+size 5134034638

model-00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0bb18f2d891f92dce325f83e31f33d53400f7da7b9a13e23b6cad2e18fe040
+size 1550919270

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test.py

@@ -0,0 +1,26 @@
+import json
+from typing import Dict
+
+from safetensors.torch import load_file, save_file
+from huggingface_hub import split_torch_state_dict_into_shards
+import torch
+import os
+
+def save_state_dict(state_dict: Dict[str, torch.Tensor], save_directory: str):
+    state_dict_split = split_torch_state_dict_into_shards(state_dict, filename_pattern='consolidated{suffix}.safetensors')
+    for filename, tensors in state_dict_split.filename_to_tensors.items():
+        shard = {tensor: state_dict[tensor] for tensor in tensors}
+        print("Saving", save_directory, filename)
+        save_file(shard, os.path.join(save_directory, filename))
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        with open(os.path.join(save_directory, "consolidated.safetensors.index.json"), "w") as f:
+            f.write(json.dumps(index, indent=2))
+
+big_file = 'consolidated.safetensors'
+loaded = load_file(big_file)
+
+save_state_dict(loaded, save_directory=f'.')

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583