MLX
Safetensors
llama
Not-For-All-Audiences
nsfw
Merge
8-bit precision
morgul commited on
Commit
1cabe15
1 Parent(s): 9876e83

Upload folder using huggingface_hub (#1)

Browse files

- 89dfb5fbb36018bd7e59d17a677694e35e4b3112178cac2e8447b63445845627 (837faddef64a484eae97371a702d3305004bb4c0)
- fcdf0996b8e6f6a61228ebe0864dbe87314b358e00ccd55e76e9915b7d10fe5c (ad40018487673c69cbf6face8d9302f86a7ed4a6)
- c63ea5d9fb6a6f8128ca81e5a400491c39809614d34792ae2f0241a400ee6561 (a3bccd961ae31d0ccc74c3114a60b0201de5161c)
- 926b0dd9bc8cf136ccc04636c093675566500b548479ee4f9772679f82249998 (48bd1f7b7b49d74e1f39258b9ee2b96dfb5a922a)
- ecd9915191b17e6e3ffc13920b96ba047702b1f681e120048c883c001c329140 (85743a3a28ec3d2e50ff922637dabea36a603ea2)
- e8063e959ff37cf790969864b594d1d3e95c8b679ec6d0734a4b799ed803f32c (5dda79702179c1f2e20b684d703c3a19052dec6c)
- e64714ae78a4735c6d43825c176c76a9d7a84042fa1f4692dbc5aa0845764423 (67a9ffd43bf2b6b9fc6b338b94d606db04e00ebd)
- 810454374b91abbed646687f13be5cdafa266a65ba99c101d46f0cc56972c27f (b7621282ccb968fe61c5b7b20ba4fb3fd31452e7)
- 6937d1dac362609134a67f14d23e70c0c8af3b10d86d2bde31ab4a927168b3c5 (7a4782075652b35011a966e7fcfb1eac21378d1a)
- 51c0200836d85d218ace6363e0b3aa450df3c54cefc35771a160a2fe9f860c81 (bc611141d3cd03e5c70ccc3c8974038191e5d3ca)
- 34eef4f1744d4e2f2fd7c3b66a76b35369564fa7e229086941ff8bea22ffce1b (33673d26b2c42a85237d2584ffc7033e66e6cb1a)
- 0f79d5b503f5b078c24a6b749c03555f0079a600b896a0de308e7e9afaaa8104 (f7dca26ae7ff537880b55530c05280f80d8d8899)
- 2704a8fb095cf90a17f6773e9cf4688201bd21b2978a96c03ee3ac7a972ef63d (907be5996e9e95fe087993652a21d0c5fb3d8880)
- 5acc4cecb8f1b8824df3fe6718127af03b3cc16a00b11ed11279ed9c3a2e9467 (3bcff243b6ee66314aba9c4c26d25a65fb5becf0)
- 0f257833049c2e528ac0ef408e16686af93a5612783d510577a8d6bd0c4997a4 (d0d56ff968497c42e5afc65e5a14852196a4d674)

README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NeverSleep/MiquMaid-v3-70B
3
+ license: cc-by-nc-4.0
4
+ tags:
5
+ - not-for-all-audiences
6
+ - nsfw
7
+ - merge
8
+ - mlx
9
+ ---
10
+
11
+ # mlx-community/MiquMaid-v3-70B
12
+
13
+ The Model [mlx-community/MiquMaid-v3-70B](https://huggingface.co/mlx-community/MiquMaid-v3-70B) was converted to MLX format from [NeverSleep/MiquMaid-v3-70B](https://huggingface.co/NeverSleep/MiquMaid-v3-70B) using mlx-lm version **0.19.0**.
14
+
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install mlx-lm
19
+ ```
20
+
21
+ ```python
22
+ from mlx_lm import load, generate
23
+
24
+ model, tokenizer = load("mlx-community/MiquMaid-v3-70B")
25
+
26
+ prompt="hello"
27
+
28
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
29
+ messages = [{"role": "user", "content": prompt}]
30
+ prompt = tokenizer.apply_chat_template(
31
+ messages, tokenize=False, add_generation_prompt=True
32
+ )
33
+
34
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
35
+ ```
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 32764,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 8
23
+ },
24
+ "quantization_config": {
25
+ "group_size": 64,
26
+ "bits": 8
27
+ },
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 1000000,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.39.3",
34
+ "use_cache": true,
35
+ "vocab_size": 32000
36
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb121df0a6a4eb4212c296dbc9c885496f937fa97d7486dc7d4deb6ef6fea0e6
3
+ size 5234277124
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6532cc442399269404dd6476ebb4c8c392f00ea088f0b315cc2cf2aa9891a7
3
+ size 5205343231
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6ee962d0e9f93321303616b7999181145f0896e17d5151bc13e24b38fad14f
3
+ size 5365774825
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e65f5be599768f197a170f9ef5dff558ec408cded9d8b455862823488c3bc58
3
+ size 5134006901
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce3f5320dc9a61805ec876fe448bb98e55768a17c11ed95544a150bcca1372b
3
+ size 5205343368
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1121fc20e03560cc8713590695ae22ce46b72e63b65796070465ff1c8a55e64b
3
+ size 5205343353
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b263e3a4f73f22a81ccba25a82aaba57bb246849841547b89f8d3fe651c0f79d
3
+ size 5365774777
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a4a6fb7d3166827372a7c1d81aaa3b2c912b20bb2960365fc37fc464124eb2
3
+ size 5134006867
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83e6943e40b9767dd353ffdd2cb1f92a074dc146dfa7fe23e81949e9a3c3421
3
+ size 5205343348
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d358c0065db4105d6b1436a7b0dd1f0d343f87e562b94bbafc02a68fdc6a07e
3
+ size 5205343371
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6afb5fb3b9155a262337482ae8cc442c2af01b9bf43e23da32de4b53c8662f
3
+ size 5365774815
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb28e871ac165cd3e9868f6999f6305363e6b2fda7e502ea261881629afe3eb
3
+ size 5134006897
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6eb929164c6c0c5bfd25b1fc0862ee836f77b607d2be29552e4ad5f07a0b10
3
+ size 5205343374
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371ec23be3bfa042db01de396b58d4b0d03d252cf6a08647d823cf3ca6ca2746
3
+ size 5323454624
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": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<unk>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }