Upload folder using huggingface_hub (#1)
Browse files- 9a4b66221b18a161763b5ac716153c927d310813b25a96587fb01bb3005dda82 (f353df37fa897d8b1d84211e728c489db2ea72e1)
- c10e9ac69fdeca7b914f1711bf0197e55ccdf5aedfa0bea27d4a41ed5f608971 (5776a38dd7d254a56009e12b62ff9d1f8e895125)
- 8b2abe08a8463da32bd28fb492d94e5bb74413a724f7d78039faa388ff51c2f0 (094fd374761e58558364406f2d73611ad890b8e3)
- README.md +37 -0
- config.json +30 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
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-2409-4bit
|
23 |
+
|
24 |
+
The Model [mlx-community/Mistral-Small-Instruct-2409-4bit](https://huggingface.co/mlx-community/Mistral-Small-Instruct-2409-4bit) 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-2409-4bit")
|
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": 4
|
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-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a374b3fb3e83b4f2c768ddf553b19664e408723bffe8b738412a00d8d62cc6cf
|
3 |
+
size 5323199440
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b7c34f20a90b65afd069c46d599c8518dd197f8048083e7ff8d44ee3bdaa59
|
3 |
+
size 5351562193
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f8b33184367b041c39d345e21472220b57c697e7cb1fc32a5aa61943c6d94dd
|
3 |
+
size 1840479982
|
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
|
|