MLX
Safetensors
llama
8-bit precision

Upload folder using huggingface_hub

#1
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: jondurbin/airoboros-33b-gpt4-1.4
3
+ datasets:
4
+ - jondurbin/airoboros-gpt4-1.4
5
+ license: cc-by-nc-4.0
6
+ tags:
7
+ - mlx
8
+ ---
9
+
10
+ # mlx-community/airoboros-33b-gpt4-1.4
11
+
12
+ The Model [mlx-community/airoboros-33b-gpt4-1.4](https://huggingface.co/mlx-community/airoboros-33b-gpt4-1.4) was converted to MLX format from [jondurbin/airoboros-33b-gpt4-1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) using mlx-lm version **0.19.0**.
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("mlx-community/airoboros-33b-gpt4-1.4")
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "eos_token_id": 1,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 6656,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 17920,
11
+ "max_position_embeddings": 2048,
12
+ "max_sequence_length": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 52,
15
+ "num_hidden_layers": 60,
16
+ "pad_token_id": -1,
17
+ "quantization": {
18
+ "group_size": 64,
19
+ "bits": 8
20
+ },
21
+ "quantization_config": {
22
+ "group_size": 64,
23
+ "bits": 8
24
+ },
25
+ "rms_norm_eps": 1e-06,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.31.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33db2208b8e0a1e79d3429956062b8ad7156d5cda8dbd7617a81a74040113a71
3
+ size 5342848326
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08aab17e5dbe969a3d2ffbeb62b6f3678729fe613ccf72a6301cdd49dbefbac5
3
+ size 5304830522
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d23f8c926892431f242f4424eaf5bb021b841de7c1b0c921c99613c68bb8cf
3
+ size 5366277919
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de8b6fa8d3f264e0b1e23c47e4539e451d3116b666cf4aac906a4cf7246bcc1
3
+ size 5341172272
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80cd2d832cc2fb6c652efc83efb9d2287252b83809bf696d572219646e8b114d
3
+ size 5337417936
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5988e2c22be019f62a41173475f3a5315c7d1ab80a16629a7e7a3a970378410f
3
+ size 5366277920
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de82c6d6a795e193a57092749721ad6fe89d0f9f9bcd313590235be403b61aa7
3
+ size 2504091644
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": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
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": true,
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }