shanginn commited on
Commit
51faa93
·
verified ·
1 Parent(s): 2c33159

Upload folder using huggingface_hub (#1)

Browse files

- e4a611c3a582a9deb656a728d3b69e324cd1b023eedb7a290fa40b664a6eca5c (b623587a3e253189226e81ea61e527a42282ed74)
- e4e804f0b3dc7db5509aa0bfcfabf63e1be1e382fa04d5d2fd14b64e7bc54260 (15b5eb2bdbe7c56f8594abcc629adb93e307721d)
- acd686e0de5ca1dbb67409016761f0d10b1ad3e312c66b8bbc65c4076b7a6f7a (cbba9c79c0482be6a00b0b6d94837ab7e07e8dda)
- 44e2eaccbbb111c4e43f870b51c35da9a28e3f1d9d159b41964f028f07efaeb2 (eabf075897d60139463d6ce84ee61ab2edb8bfe5)
- 0fe4ceec9b5aab281f49e345e528475438f974e82a178a2815d8c1548390e8c2 (8c1bf7c1b52701450ac92d9284b1df4221a47380)
- 238f872f452dcb4309e54ae4e6d6a11a003dff45c4a09ed58b1772d8f7242d3f (c6d7052b6cfcba896a19ddef91f0a964c213421e)
- a9efb0eefed48c40f05cbb22b6b082d197e581103c2ac42d7e622b793988e4ad (d3a8312beb4ca046b817f9cff044a2bfdd3a693c)
- 3586c445893aa2b117c3cb1c6290d723d15095ccd1ef6c29278935a014fbf978 (f13646de8ad8743b5add948703e750af7fba8646)

README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FluffyKaeloky/Luminum-v0.1-123B
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+ - mlx
8
+ ---
9
+
10
+ # shanginn/Luminum-v0.1-123B-mlx-quantized-2bit
11
+
12
+ The Model [shanginn/Luminum-v0.1-123B-mlx-quantized-2bit](https://huggingface.co/shanginn/Luminum-v0.1-123B-mlx-quantized-2bit) was converted to MLX format from [FluffyKaeloky/Luminum-v0.1-123B](https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B) using mlx-lm version **0.19.2**.
13
+
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install mlx-lm
18
+ ```
19
+
20
+ ```python
21
+ from mlx_lm import load, generate
22
+
23
+ model, tokenizer = load("shanginn/Luminum-v0.1-123B-mlx-quantized-2bit")
24
+
25
+ prompt="hello"
26
+
27
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
28
+ messages = [{"role": "user", "content": prompt}]
29
+ prompt = tokenizer.apply_chat_template(
30
+ messages, tokenize=False, add_generation_prompt=True
31
+ )
32
+
33
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
34
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 12288,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 96,
16
+ "num_hidden_layers": 88,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 64,
20
+ "bits": 2
21
+ },
22
+ "quantization_config": {
23
+ "group_size": 64,
24
+ "bits": 2
25
+ },
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32768
34
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ea0156c817df0ad25a2bfcae85d9aa34a43b45c6843b5af54fd9af75d0af40
3
+ size 5368020732
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f22d27ba0b2f6ba11f7752f63251189616352f20212a8b987141776f4dd50c7
3
+ size 5352292317
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3c271b02d39355c46f11b52abdd657f6873e7446958ba65c3c27d00b09788a
3
+ size 5301173605
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39466817197d0637f19096524b13bf9d800ca4fdef62c0331e7523c279c1bfb
3
+ size 5356274234
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b447d4689de2bcc87a2dc1cd17a1f2e2d166ff12e09b37e668bcee10bf49f5
3
+ size 5348359845
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0616626789b7ce98244c37769221ad3127b89a87b764828a0b12a78f63a30a
3
+ size 5301173585
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54ce9ccddc2c3edc93cc65e20a4556aab1fd974482347d5abb6f3320ee1424e
3
+ size 5356274240
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f35ec5322d769b79081f3c7d9f8fa58b152b8ec50ec73cc0523d650bb9b0e8
3
+ size 935981527
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff