prince-canuma commited on
Commit
bf09a07
·
verified ·
1 Parent(s): 6d62f17

Upload folder using huggingface_hub (#1)

Browse files

- 9df7b5d0c44dd218f79162005111e4a5c4d2b1fbabe7c093948cb434b3a05a3b (3e3d8bdbea50d07eeebd103dd97f671e42f9f0b3)
- 86c0063d06e8fc36c7c97faa493c3c8f52c85c4e8b4b05dd4d755023379524d4 (2a680895c8f63ce46d3b346abb1a1bead7ca21cb)
- 3412bb1ff6b478c1d1862ee45990d4870226b7c1cd16f440f0766d9baf4aeb30 (9011f7e9bdf9c47a83e8455b2ac10267e0b2b568)
- 176dfc6b32fefdcbfe0288ba4d3e9f89a6f1ebd317bb9b664bee276b6271a2ac (aa7462657ebec9e5562252bb65789e4713ea558a)
- f54f9fda035cf58e1c055278b16a9cbe67f3ceaba685db97f2e104919fc776af (7808aaf1ec97e2462ae32e9d5e2d89207842397d)
- 046814e24c0cbddccb361d14ed53275ba446b568ba5b38fc819acb6401cd1d54 (99f0b765384923f3b59c17a06f363dfd8ef29530)

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
+ license_name: mrl
15
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
16
+ tags:
17
+ - mlx
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-Small-Instruct-2409-8bit
23
+
24
+ The Model [mlx-community/Mistral-Small-Instruct-2409-8bit](https://huggingface.co/mlx-community/Mistral-Small-Instruct-2409-8bit) was converted to MLX format from [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409) using mlx-lm version **0.18.1**.
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-Small-Instruct-2409-8bit")
36
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
37
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 48,
16
+ "num_hidden_layers": 56,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 64,
20
+ "bits": 8
21
+ },
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000000.0,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.45.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32768
30
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6432cd357ef39ef9f7cf214295e08c2ca5a808941fb0a41b1c23b2ee96bee86d
3
+ size 5281218750
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c905be25cba84fbca938979cfd670967e3043f7d6f5eb16cbf6ea7b56fc416e
3
+ size 5348090886
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9253c62f5f504775a8c71dc0fe581db5700c27701819ee3253ea832875728dca
3
+ size 5334720842
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5554fa364e1bd723fff0cceb7e377d87e111efd1cf0b7306f0d47cdc4b4789e6
3
+ size 5281219421
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6965f2fccabdcd2e0cae6479a80c749cf2185e3243f1bf2875826356b4b9ed
3
+ size 2393286368
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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