prince-canuma
commited on
Commit
•
ceac722
1
Parent(s):
41c1acb
Upload folder using huggingface_hub
Browse files- README.md +21 -0
- config.json +88 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.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 +44 -0
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- mlx
|
5 |
+
---
|
6 |
+
|
7 |
+
# mlx-community/WizardLM-2-8x22B-4bit
|
8 |
+
This model was converted to MLX format from [`prince-canuma/WizardLM-2-8x22B`]() using mlx-lm version **0.9.0**.
|
9 |
+
Refer to the [original model card](https://huggingface.co/prince-canuma/WizardLM-2-8x22B) for more details on the model.
|
10 |
+
## Use with mlx
|
11 |
+
|
12 |
+
```bash
|
13 |
+
pip install mlx-lm
|
14 |
+
```
|
15 |
+
|
16 |
+
```python
|
17 |
+
from mlx_lm import load, generate
|
18 |
+
|
19 |
+
model, tokenizer = load("mlx-community/WizardLM-2-8x22B-4bit")
|
20 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
21 |
+
```
|
config.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_cross_attention": false,
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bad_words_ids": null,
|
8 |
+
"begin_suppress_tokens": null,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"chunk_size_feed_forward": 0,
|
11 |
+
"cross_attention_hidden_size": null,
|
12 |
+
"decoder_start_token_id": null,
|
13 |
+
"diversity_penalty": 0.0,
|
14 |
+
"do_sample": false,
|
15 |
+
"early_stopping": false,
|
16 |
+
"encoder_no_repeat_ngram_size": 0,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"exponential_decay_length_penalty": null,
|
19 |
+
"finetuning_task": null,
|
20 |
+
"forced_bos_token_id": null,
|
21 |
+
"forced_eos_token_id": null,
|
22 |
+
"hidden_act": "silu",
|
23 |
+
"hidden_size": 6144,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 16384,
|
30 |
+
"is_decoder": false,
|
31 |
+
"is_encoder_decoder": false,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1
|
35 |
+
},
|
36 |
+
"length_penalty": 1.0,
|
37 |
+
"max_length": 20,
|
38 |
+
"max_position_embeddings": 65536,
|
39 |
+
"min_length": 0,
|
40 |
+
"model_type": "mixtral",
|
41 |
+
"no_repeat_ngram_size": 0,
|
42 |
+
"num_attention_heads": 48,
|
43 |
+
"num_beam_groups": 1,
|
44 |
+
"num_beams": 1,
|
45 |
+
"num_experts_per_tok": 2,
|
46 |
+
"num_hidden_layers": 56,
|
47 |
+
"num_key_value_heads": 8,
|
48 |
+
"num_local_experts": 8,
|
49 |
+
"num_return_sequences": 1,
|
50 |
+
"output_attentions": false,
|
51 |
+
"output_hidden_states": false,
|
52 |
+
"output_router_logits": false,
|
53 |
+
"output_scores": false,
|
54 |
+
"pad_token_id": null,
|
55 |
+
"prefix": null,
|
56 |
+
"problem_type": null,
|
57 |
+
"pruned_heads": {},
|
58 |
+
"quantization": {
|
59 |
+
"group_size": 64,
|
60 |
+
"bits": 4
|
61 |
+
},
|
62 |
+
"remove_invalid_values": false,
|
63 |
+
"repetition_penalty": 1.0,
|
64 |
+
"return_dict": true,
|
65 |
+
"return_dict_in_generate": false,
|
66 |
+
"rms_norm_eps": 1e-05,
|
67 |
+
"rope_theta": 1000000,
|
68 |
+
"router_aux_loss_coef": 0.001,
|
69 |
+
"router_jitter_noise": 0.0,
|
70 |
+
"sep_token_id": null,
|
71 |
+
"sliding_window": null,
|
72 |
+
"suppress_tokens": null,
|
73 |
+
"task_specific_params": null,
|
74 |
+
"temperature": 1.0,
|
75 |
+
"tf_legacy_loss": false,
|
76 |
+
"tie_encoder_decoder": false,
|
77 |
+
"tie_word_embeddings": false,
|
78 |
+
"tokenizer_class": null,
|
79 |
+
"top_k": 50,
|
80 |
+
"top_p": 1.0,
|
81 |
+
"torch_dtype": "bfloat16",
|
82 |
+
"torchscript": false,
|
83 |
+
"transformers_version": "4.39.3",
|
84 |
+
"typical_p": 1.0,
|
85 |
+
"use_bfloat16": false,
|
86 |
+
"use_cache": false,
|
87 |
+
"vocab_size": 32000
|
88 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57decc815bb7cbc9a159c96699d840c1a30bd39ada288eae5ed43d23726ff522
|
3 |
+
size 5348243543
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2094da14c971b98f120bdbd6db9265143465df49cf2464729690e1fe47cab9c4
|
3 |
+
size 5351416647
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e78abeb391de23bd286de34c6ce6e82a97be65942497ac74120fd2646d31a0e9
|
3 |
+
size 5351416767
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fc1882b2ccc0510738dbb5f947d643dd14d36a2b47b28af90a1b55c8bfabc50
|
3 |
+
size 5358370676
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0729116cf16ec741686f87f4eed1b09e0c34463d51ba9a6509020dbf655d55eb
|
3 |
+
size 5351416986
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe8faaa35a96d0ff50d203f4fa8ad2176bcc1ef6527fa9829ad9c165f8668d28
|
3 |
+
size 5351416970
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287b31a8d239a205df69dda3ac6aca2f31ae3f78fb4ef92f2fa3607bbf796a32
|
3 |
+
size 5351416986
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f6ac42867b0b8cb29505dfe6a55f6e2eb7789e5ceccae437d225fd7b49f5d3e
|
3 |
+
size 5351416926
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58e0e87a8fd243028349bc77ce32937d4750b5f9559cde711e863db3a760eac9
|
3 |
+
size 5358370660
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00025bf2f8b1cd1aa2813dce7bbec9e2e9a9096eaf19dd02d50eba324c9b5261
|
3 |
+
size 5351416978
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a43867d1fd00682495e65928f3de45ae5723c3d8ebd7cb6d9c1fea8b0835be6
|
3 |
+
size 5351416972
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:380c0be71f611fc5af74c5255a43e58bd1a85fc2515050904bc1df5035971968
|
3 |
+
size 5351416998
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a499b562d351d8d17b24dd257d9d2b67ed5dc5fde5ddbdfc49be2961bab1951
|
3 |
+
size 5351416966
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0edacf1ff110b68f72ef7dbf166ba457d735fd74f9b24608fc6add8a95c4cbe5
|
3 |
+
size 5358370678
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6540ce611163893ac17297a426077eda85590bd9ab4062f05a0caf4f742d4f54
|
3 |
+
size 4449777255
|
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": "<unk>",
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|