3thn commited on
Commit
161ac6f
1 Parent(s): 7855099

Upload folder using huggingface_hub (#1)

Browse files

- aa4e7cd5e9dc6f1c81e409be233840a9d172efd6e09b64a70d0f3256e7c5b1aa (62764f10e54eb30b0dece6259f19bce008a8e7de)
- 0622b29b65106cdb671668e76631a6bfb7b04261e17d2bba2d729689088bae0c (16bec57f06fe0ec3a64d1d9db5b81dbc2e08e127)
- 4659ab422465ec034640cbf226218c48c9ba59b092b685feaaa12b8c097ba440 (8e6f7952f987fbc04bf1ca4264efaf31de36c1e6)
- ef672fa25f4ce0a149f74a746362c262d2f59bb49e484ad16e95220e7a707418 (c10e9ac940bd64ca72599acefb27fcf13d8b39a5)
- 7ef8752cceef00beac2fda117c355e506d66d4ebe46b56d812540a6a5bc73659 (ab7aad729e43f141ff94bf18d6bb93f714e1766d)
- 6a8deaf59583f17c616f2ee21e1505458fb23d0086cde699a114ba2bf1388f9c (dced3d698c2403bbe5e13e84a77269ca939c4193)

README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ - axolotl
8
+ - mlx
9
+ base_model: mistral-community/Mixtral-8x22B-v0.1
10
+ datasets:
11
+ - cognitivecomputations/Dolphin-2.9
12
+ - teknium/OpenHermes-2.5
13
+ - m-a-p/CodeFeedback-Filtered-Instruction
14
+ - cognitivecomputations/dolphin-coder
15
+ - cognitivecomputations/samantha-data
16
+ - microsoft/orca-math-word-problems-200k
17
+ - abacusai/SystemChat-1.1
18
+ - Locutusque/function-calling-chatml
19
+ - internlm/Agent-FLAN
20
+ model-index:
21
+ - name: out
22
+ results: []
23
+ ---
24
+
25
+ # mlx-community/dolphin-2.9.1-mixtral-1x22b-8bit
26
+ This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9.1-mixtral-1x22b`]() using mlx-lm version **0.12.1**.
27
+ Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-mixtral-1x22b) for more details on the model.
28
+ ## Use with mlx
29
+
30
+ ```bash
31
+ pip install mlx-lm
32
+ ```
33
+
34
+ ```python
35
+ from mlx_lm import load, generate
36
+
37
+ model, tokenizer = load("mlx-community/dolphin-2.9.1-mixtral-1x22b-8bit")
38
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
39
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MixtralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32000,
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": 1,
16
+ "num_hidden_layers": 56,
17
+ "num_key_value_heads": 8,
18
+ "num_local_experts": 1,
19
+ "output_router_logits": false,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 8
23
+ },
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_theta": 1000000,
26
+ "router_aux_loss_coef": 0.001,
27
+ "router_jitter_noise": 0.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.40.2",
32
+ "use_cache": false,
33
+ "vocab_size": 32002
34
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0554bd8dc6b8eb2331d0a0087b947ad4e5571ee8e1a814fccb4a6d5f39db56b
3
+ size 5276309511
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327f52742b4efe07ba10f6889707b61df837ea17e50f375ea61ff8d0bdbd5e59
3
+ size 5348175408
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7204ac1da271b50b06983fe43abfb22023636c209ec8bc95d2a0e34eb5542e5
3
+ size 5334812259
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2f585d46f08a0611d2104e4fa9f2f5eb7034f3df8ca1ebe3b885f5347ad933
3
+ size 5281310710
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1fe850ddad034a2c0bae8cf76092bec77abbb8f49548fa3de6049f17c2d967
3
+ size 2388321099
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": "<|im_end|>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "<|im_end|>",
51
+ "legacy": true,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": false
59
+ }