3thn commited on
Commit
5c0e66d
1 Parent(s): bd7a64b

Upload folder using huggingface_hub (#1)

Browse files

- 0aa1f61794e17ca7db621f1ba7c655831095f45a3b55925bda1502e15b60018a (694af08185a40480005921d97f1432a20facf1e6)
- 1ef769e0b44030f477cb5fbb94b350386d1f7a274da0b32dc31d001a7645b2fe (f3178ce982e2b1a5964df92b07b6964426245be8)
- 9acc0cf36c92a6428ef7929a1ddcf5eb9c40113224c168698b4afecbbd802f6c (3910f28e13002749eed1efcc6065a2cfe88b9e15)
- e4ed91ff183518dfb14f974785571a662d7451fc1fc1e5dc16291e5addda3f49 (99e1545b2033ff90f9dde33d172f28f120cfe417)
- 6d392797d3072ac873e70c92fb31f32c6542be8fdf4ddd1e5ff216d61811f9b8 (bfac4340d3171bc10ff8ebb910d7016662389017)
- 278ec9dd57409cffee796d8ac394ea4417025a10d1e5acf820a1f333d7935bdd (efa56316bfd4c9bc1032a3d75fe1ca9e5a0d793b)
- ab0655e3701f394a74d8af80c7cf28d9c2c05040093ae54870a443a10e0c3736 (467d4abd83f87c97750f797031fa25c6582351be)
- ddeab67628dafc592422ced550b7e3036ca7d6886767a7175dd8e903d3b2eeec (e4f0685e3fc3091b9ed7359f9bb259506758beae)
- ad4ee3985be34ca84f36ee43cfe4cae968dd869968136ece1bbd020a6f12b023 (ce5b5448ed36767c980c87fb161101bd82d6b70f)
- cf5d32303f02921b0f03d7f2e15448921b22fe8e35ca97bb9aa30fdbea2f7852 (e961b67f67a7a5346011726f2d6b6fbb24f65261)
- ff3c22635cd083172db059f3578c888b36d810ddf79b8be8560051ae8798afd3 (3d3cf9886009f48afdad466e90466450179e33c1)
- 2297707eeaaa88f8ff6cb77b71293c77ee308bd92593928fd6dbcb9ba2685fcb (89475aa7f7a4d78b45b019214ec133af207b1c01)
- 0fd31733e8773803b25f217957fe955d0ea00aa2a13cd337169d4e0b11a4f241 (1e055224b983caf2bb353d2e7f089903ca0e1fcf)
- 9c99a2a98de6ee66cb0192746a2218947fc28aa334945749b0d35826f644b2ee (d9138923c16d4ab35978f06ee474a3bf739b37c9)
- 73d8eff6a7ca460f8c8bc296da8bcda371e818ebd1f2abde28a030ddba3876cb (18f191a8bbfc13766f9830316a35b391a91c17e3)
- a1d9931bf29043ec9dd22125fe7abac827ec9b53a5d1c21e9880f823d3b4ae13 (634c695d66ca24d190cecbd4faec5e665be0cd9d)

README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - generated_from_trainer
5
+ - axolotl
6
+ - mlx
7
+ base_model: Qwen/Qwen2-72B
8
+ datasets:
9
+ - cognitivecomputations/Dolphin-2.9
10
+ - teknium/OpenHermes-2.5
11
+ - m-a-p/CodeFeedback-Filtered-Instruction
12
+ - cognitivecomputations/dolphin-coder
13
+ - cognitivecomputations/samantha-data
14
+ - microsoft/orca-math-word-problems-200k
15
+ - Locutusque/function-calling-chatml
16
+ - internlm/Agent-FLAN
17
+ license_name: tongyi-qianwen
18
+ license_link: https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
19
+ ---
20
+
21
+ # mlx-community/dolphin-2.9.2-qwen2-72b-8bit
22
+ This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9.2-qwen2-72b`]() using mlx-lm version **0.12.1**.
23
+ Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-72b) for more details on the model.
24
+ ## Use with mlx
25
+
26
+ ```bash
27
+ pip install mlx-lm
28
+ ```
29
+
30
+ ```python
31
+ from mlx_lm import load, generate
32
+
33
+ model, tokenizer = load("mlx-community/dolphin-2.9.2-qwen2-72b-8bit")
34
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
35
+ ```
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 8192,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 29568,
11
+ "max_position_embeddings": 131072,
12
+ "max_window_layers": 28,
13
+ "model_type": "qwen2",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "quantization": {
18
+ "group_size": 64,
19
+ "bits": "8"
20
+ },
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": 4096,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.40.2",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 152064
30
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542de67b0e0f42cafe2f8fb035bcebcaf8b810b9091c7536cd4b36f06c58d4a5
3
+ size 5214291418
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91444a9cde8a28becbc5409be3f766c440978f33139332453779e733798a38e3
3
+ size 5177560124
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e19cb145f5c61b6c4ea27d7cbae9a1e417dda8554ffd87995a995aca3126ab6
3
+ size 5338047575
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb3fc7f8e246eb676da108ee1537e52bcc7b943e251ba97e9111e8c25acc0f9
3
+ size 5338047581
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6a64600a747482c29575bea6242e59ca35946edba4effba01c33d798bbab91
3
+ size 5177560270
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe083395124b131b15626cf1fd4e58af78ca7a813d2539341cdcc284159b1305
3
+ size 5338047562
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531d8db3c9b91d06b7bc0c61c41a90eebd8e4e4b2adccb9be1509e865d364481
3
+ size 5338047557
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14f9de3590f03dff19828a35d5b892f1a29382f880257b86f228730c281a9a0
3
+ size 5177560278
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1143823c5dcdfa3417c6f746fba6f9067c34e9386e09096fe7f6642a1a7f5ea
3
+ size 5338047594
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b863f5037027ad89b5ac4795912c0aaeca7fec2c2be9f01c01bb129ab6b94f2
3
+ size 5338047549
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea650a9a1117ec874cf05a2d8ef6674a363dcb2a8e0802963e905ce9cfeb6b4d
3
+ size 5177560280
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f392f31dffe7416664d68730ba0af17ef7ea6e5083b8f3e2cadb3925944be954
3
+ size 5338047560
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36f0deeba0b0451cc5fe8aa5431354fb78bbb4434f7540a62bf801edacd24c7
3
+ size 5338047535
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84e6f015be9c125d88a2758a1337c7764bb7e9fb70df4c2c251755c5cf0246f
3
+ size 5177560290
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfb652ffccdfd68607f3c73579a32eb9e217ac2ebf72a00497ffec04e445af3
3
+ size 3446110912
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "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 %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff