Upload folder using huggingface_hub

#1
README.md CHANGED
@@ -1,15 +1,19 @@
1
  ---
 
 
 
 
 
 
2
  license: apache-2.0
3
  tags:
4
  - mlx
5
  ---
6
 
7
  # mlx-community/Mixtral-8x22B-Instruct-v0.1-4bit
8
- This model was converted to MLX format from [`mistralai/Mixtral-8x22B-Instruct-v0.1`]() using mlx-lm version **0.9.0**.
9
 
10
- Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
11
 
12
- Refer to the [original model card](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) for more details on the model.
13
  ## Use with mlx
14
 
15
  ```bash
 
1
  ---
2
+ language:
3
+ - en
4
+ - es
5
+ - it
6
+ - de
7
+ - fr
8
  license: apache-2.0
9
  tags:
10
  - mlx
11
  ---
12
 
13
  # mlx-community/Mixtral-8x22B-Instruct-v0.1-4bit
 
14
 
15
+ The Model [mlx-community/Mixtral-8x22B-Instruct-v0.1-4bit](https://huggingface.co/mlx-community/Mixtral-8x22B-Instruct-v0.1-4bit) was converted to MLX format from [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) using mlx-lm version **0.14.0**.
16
 
 
17
  ## Use with mlx
18
 
19
  ```bash
config.json CHANGED
@@ -1,87 +1,33 @@
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": 1000000.0,
68
  "router_aux_loss_coef": 0.001,
69
- "sep_token_id": null,
70
  "sliding_window": null,
71
- "suppress_tokens": null,
72
- "task_specific_params": null,
73
- "temperature": 1.0,
74
- "tf_legacy_loss": false,
75
- "tie_encoder_decoder": false,
76
  "tie_word_embeddings": false,
77
- "tokenizer_class": null,
78
- "top_k": 50,
79
- "top_p": 1.0,
80
  "torch_dtype": "bfloat16",
81
- "torchscript": false,
82
- "transformers_version": "4.39.3",
83
- "typical_p": 1.0,
84
- "use_bfloat16": false,
85
  "use_cache": true,
86
  "vocab_size": 32768
87
  }
 
1
  {
 
2
  "architectures": [
3
  "MixtralForCausalLM"
4
  ],
5
  "attention_dropout": 0.0,
 
 
6
  "bos_token_id": 1,
 
 
 
 
 
 
 
7
  "eos_token_id": 2,
 
 
 
 
8
  "hidden_act": "silu",
9
  "hidden_size": 6144,
 
 
 
 
10
  "initializer_range": 0.02,
11
  "intermediate_size": 16384,
 
 
 
 
 
 
 
 
12
  "max_position_embeddings": 65536,
 
13
  "model_type": "mixtral",
 
14
  "num_attention_heads": 48,
 
 
15
  "num_experts_per_tok": 2,
16
  "num_hidden_layers": 56,
17
  "num_key_value_heads": 8,
18
  "num_local_experts": 8,
 
 
 
19
  "output_router_logits": false,
 
 
 
 
 
20
  "quantization": {
21
  "group_size": 64,
22
  "bits": 4
23
  },
 
 
 
 
24
  "rms_norm_eps": 1e-05,
25
  "rope_theta": 1000000.0,
26
  "router_aux_loss_coef": 0.001,
 
27
  "sliding_window": null,
 
 
 
 
 
28
  "tie_word_embeddings": false,
 
 
 
29
  "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.38.0",
 
 
 
31
  "use_cache": true,
32
  "vocab_size": 32768
33
  }
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb00f81c22e84f8628741581b2987b1df5ce708cff9c75c57da60b3f49e0d44
3
+ size 5294456945
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52aac1cb6c0ea90b48aa14f922acde6d554fb110dcf310b45832c38d9ea4ddb9
3
+ size 5181235243
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29ab95b851ac9b885c26204634a920823a889de187982871e0d9ce880a34af2
3
+ size 5181235208
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ba83e478b9ca58288bf852b09c95607c777b00b873134e5a383c561384157e
3
+ size 5131635931
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ea5e7ed82936a2db1552948c468d906bd0aa4c02ac15517d9a1d93e4c5aa85
3
+ size 5181235326
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfc46bad182f82b317262e3edb4417a4f3223424299a6e349a495f8891ec293
3
+ size 5181235312
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0243b82ab8e8c73574241f182c2eed79b80033fa28f7de4c9eb4d9e3ace85e
3
+ size 5131635949
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0482cd40b6483eca40ba6e46b9ad5d7e8fb936bec8caadbd5d0e8535e2a1de1
3
+ size 5181235342
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503ba074eadbed6109d6fb57813837a26611c4e83c3f25f9d9537a9a451da9c7
3
+ size 5181235294
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f30c130dd5f537321695368c0472a7d4d61eaf621489c794ad81da7cdfbba0
3
+ size 5131635917
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b34b30c966183f302d793d269f9e3c306ba50c5e785ca8056bc09a8a4a0a862
3
+ size 5181235346
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3f436e96b274d006048d55761cfbd036a471e517f3f2b79c49c89cf48e8f82
3
+ size 5181235292
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa09047699ab624c75d73cefa4f03ab3e2ace25f45c5080b1380a1600ddcc94
3
+ size 5131635939
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed1c8918e483f47bb6b9f3404875c2d4e1cd27af6706358944ab4e49849d115
3
+ size 5181235376
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34050a8e23ffb50edca240f64af73d46e532f4064c1b54b12c2ce21442f6563
3
+ size 5181235324
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef97915a74a5e172c21766b15e8ae734fdca4368b07bcd08b4455cce4f06357
3
+ size 1472239423
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.json CHANGED
@@ -76,8 +76,8 @@
76
  "special": true
77
  },
78
  {
79
- "id": 9,
80
- "content": "[/TOOL_RESULTS]",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
@@ -85,8 +85,8 @@
85
  "special": true
86
  },
87
  {
88
- "id": 32768,
89
- "content": "[TOOL_RESULT]",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
 
76
  "special": true
77
  },
78
  {
79
+ "id": 8,
80
+ "content": "[TOOL_RESULTS]",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
 
85
  "special": true
86
  },
87
  {
88
+ "id": 9,
89
+ "content": "[/TOOL_RESULTS]",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -66,16 +66,16 @@
66
  "single_word": false,
67
  "special": true
68
  },
69
- "9": {
70
- "content": "[/TOOL_RESULTS]",
71
  "lstrip": false,
72
  "normalized": true,
73
  "rstrip": false,
74
  "single_word": false,
75
  "special": true
76
  },
77
- "32768": {
78
- "content": "[TOOL_RESULT]",
79
  "lstrip": false,
80
  "normalized": true,
81
  "rstrip": false,
@@ -85,7 +85,16 @@
85
  },
86
  "additional_special_tokens": [],
87
  "bos_token": "<s>",
88
- "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 %}",
 
 
 
 
 
 
 
 
 
89
  "clean_up_tokenization_spaces": false,
90
  "eos_token": "</s>",
91
  "legacy": true,
 
66
  "single_word": false,
67
  "special": true
68
  },
69
+ "8": {
70
+ "content": "[TOOL_RESULTS]",
71
  "lstrip": false,
72
  "normalized": true,
73
  "rstrip": false,
74
  "single_word": false,
75
  "special": true
76
  },
77
+ "9": {
78
+ "content": "[/TOOL_RESULTS]",
79
  "lstrip": false,
80
  "normalized": true,
81
  "rstrip": false,
 
85
  },
86
  "additional_special_tokens": [],
87
  "bos_token": "<s>",
88
+ "chat_template": [
89
+ {
90
+ "name": "default",
91
+ "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 %}"
92
+ },
93
+ {
94
+ "name": "tool_use",
95
+ "template": "{{bos_token}}{% set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}{% for message in messages %}{% if message['role'] == 'user' %}{% if message == user_messages[-1] %}{% if tools %}{{'[AVAILABLE_TOOLS]'+ tools|string + '[/AVAILABLE_TOOLS]'}}{% endif %}{{ '[INST]' + message['content'] + '[/INST]' }}{% else %}{{ '[INST]' + message['content'] + '[/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% elif message['role'] == 'tool_results' %}{{'[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]'}}{% elif message['role'] == 'tool_calls' %}{{'[TOOL_CALLS]' + message['content']|string + eos_token}}{% endif %}{% endfor %}"
96
+ }
97
+ ],
98
  "clean_up_tokenization_spaces": false,
99
  "eos_token": "</s>",
100
  "legacy": true,