Upload folder using huggingface_hub (#1)
Browse files- 2765105860eab2adcd6d8578014b70b5e34262dd131da57513ca9be436bfdb4b (d60f86a632a7c59f01c2571af3943d922672c3aa)
- 83c97249e51f4f035955434d56d8fcbf5219cec8adc7fde7268fa2d242d0fe9e (b093d9532b8bd33c32d935110ad403630ea91186)
- ba325e146065903d1948458da7b813ec771c74c810dd8ed20befe4b7234756ce (5bf7cfdd59f4d51df4f20af3a2ef82e74f1535cc)
- .gitattributes +1 -0
- README.md +24 -0
- config.json +87 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_strategy.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +195 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0
|
4 |
+
tags:
|
5 |
+
- mlx
|
6 |
+
---
|
7 |
+
|
8 |
+
# GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx
|
9 |
+
|
10 |
+
This quantized low-bit model [GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx) was converted to MLX format from [`GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0`](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0) using gbx-lm version **0.3.5**.
|
11 |
+
Refer to the [original model card](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0) for more details on the model.
|
12 |
+
|
13 |
+
## Use with mlx
|
14 |
+
|
15 |
+
```bash
|
16 |
+
pip install gbx-lm
|
17 |
+
```
|
18 |
+
|
19 |
+
```python
|
20 |
+
from gbx_lm import load, generate
|
21 |
+
|
22 |
+
model, tokenizer = load("GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx")
|
23 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
24 |
+
```
|
config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": false,
|
3 |
+
"add_cross_attention": false,
|
4 |
+
"architectures": [
|
5 |
+
"Qwen2ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bad_words_ids": null,
|
9 |
+
"begin_suppress_tokens": null,
|
10 |
+
"bos_token_id": 151643,
|
11 |
+
"chunk_size_feed_forward": 0,
|
12 |
+
"cross_attention_hidden_size": null,
|
13 |
+
"decoder_start_token_id": null,
|
14 |
+
"diversity_penalty": 0.0,
|
15 |
+
"do_sample": false,
|
16 |
+
"early_stopping": false,
|
17 |
+
"encoder_no_repeat_ngram_size": 0,
|
18 |
+
"eos_token_id": 151643,
|
19 |
+
"exponential_decay_length_penalty": null,
|
20 |
+
"finetuning_task": null,
|
21 |
+
"forced_bos_token_id": null,
|
22 |
+
"forced_eos_token_id": null,
|
23 |
+
"hidden_act": "silu",
|
24 |
+
"hidden_size": 5120,
|
25 |
+
"id2label": {
|
26 |
+
"0": "LABEL_0",
|
27 |
+
"1": "LABEL_1"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 13824,
|
31 |
+
"is_decoder": false,
|
32 |
+
"is_encoder_decoder": false,
|
33 |
+
"label2id": {
|
34 |
+
"LABEL_0": 0,
|
35 |
+
"LABEL_1": 1
|
36 |
+
},
|
37 |
+
"length_penalty": 1.0,
|
38 |
+
"max_length": 20,
|
39 |
+
"max_position_embeddings": 131072,
|
40 |
+
"max_window_layers": 48,
|
41 |
+
"min_length": 0,
|
42 |
+
"model_type": "qwen2",
|
43 |
+
"no_repeat_ngram_size": 0,
|
44 |
+
"num_attention_heads": 40,
|
45 |
+
"num_beam_groups": 1,
|
46 |
+
"num_beams": 1,
|
47 |
+
"num_hidden_layers": 48,
|
48 |
+
"num_key_value_heads": 8,
|
49 |
+
"num_return_sequences": 1,
|
50 |
+
"output_attentions": false,
|
51 |
+
"output_hidden_states": false,
|
52 |
+
"output_scores": false,
|
53 |
+
"pad_token_id": null,
|
54 |
+
"prefix": null,
|
55 |
+
"problem_type": null,
|
56 |
+
"pruned_heads": {},
|
57 |
+
"quantization": {
|
58 |
+
"group_size": null,
|
59 |
+
"bits": null
|
60 |
+
},
|
61 |
+
"remove_invalid_values": false,
|
62 |
+
"repetition_penalty": 1.0,
|
63 |
+
"return_dict": true,
|
64 |
+
"return_dict_in_generate": false,
|
65 |
+
"rms_norm_eps": 1e-05,
|
66 |
+
"rope_scaling": null,
|
67 |
+
"rope_theta": 1000000.0,
|
68 |
+
"sep_token_id": null,
|
69 |
+
"sliding_window": null,
|
70 |
+
"suppress_tokens": null,
|
71 |
+
"task_specific_params": null,
|
72 |
+
"temperature": 1.0,
|
73 |
+
"tf_legacy_loss": false,
|
74 |
+
"tie_encoder_decoder": false,
|
75 |
+
"tie_word_embeddings": false,
|
76 |
+
"tokenizer_class": null,
|
77 |
+
"top_k": 50,
|
78 |
+
"top_p": 1.0,
|
79 |
+
"torch_dtype": "float16",
|
80 |
+
"torchscript": false,
|
81 |
+
"transformers_version": "4.47.0",
|
82 |
+
"typical_p": 1.0,
|
83 |
+
"use_bfloat16": false,
|
84 |
+
"use_cache": true,
|
85 |
+
"use_sliding_window": false,
|
86 |
+
"vocab_size": 152064
|
87 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639ed285e5166e7d6aa60a617cf7a7a66e82e7e352763eab8699b1c3663df72b
|
3 |
+
size 5364709767
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c65cd2fffaf3421cdfd7522a1e4704c2ae3ce191c8aa5c5c737a1646609ed55
|
3 |
+
size 4778920604
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quant_strategy.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": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
3 |
+
size 11422778
|
tokenizer_config.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"151643": {
|
7 |
+
"content": "<|end▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"151644": {
|
15 |
+
"content": "<|User|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": false
|
21 |
+
},
|
22 |
+
"151645": {
|
23 |
+
"content": "<|Assistant|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"151646": {
|
31 |
+
"content": "<|begin▁of▁sentence|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"151647": {
|
39 |
+
"content": "<|EOT|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"151648": {
|
47 |
+
"content": "<think>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"151649": {
|
55 |
+
"content": "</think>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"151650": {
|
63 |
+
"content": "<|quad_start|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"151651": {
|
71 |
+
"content": "<|quad_end|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"151652": {
|
79 |
+
"content": "<|vision_start|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"151653": {
|
87 |
+
"content": "<|vision_end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"151654": {
|
95 |
+
"content": "<|vision_pad|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"151655": {
|
103 |
+
"content": "<|image_pad|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"151656": {
|
111 |
+
"content": "<|video_pad|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"151657": {
|
119 |
+
"content": "<tool_call>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"151658": {
|
127 |
+
"content": "</tool_call>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"151659": {
|
135 |
+
"content": "<|fim_prefix|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"151660": {
|
143 |
+
"content": "<|fim_middle|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"151661": {
|
151 |
+
"content": "<|fim_suffix|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"151662": {
|
159 |
+
"content": "<|fim_pad|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"151663": {
|
167 |
+
"content": "<|repo_name|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"151664": {
|
175 |
+
"content": "<|file_sep|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
}
|
182 |
+
},
|
183 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin��>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
|
185 |
+
"clean_up_tokenization_spaces": false,
|
186 |
+
"eos_token": "<|end▁of▁sentence|>",
|
187 |
+
"extra_special_tokens": {},
|
188 |
+
"legacy": true,
|
189 |
+
"model_max_length": 16384,
|
190 |
+
"pad_token": "<|end▁of▁sentence|>",
|
191 |
+
"sp_model_kwargs": {},
|
192 |
+
"tokenizer_class": "LlamaTokenizer",
|
193 |
+
"unk_token": null,
|
194 |
+
"use_default_system_prompt": false
|
195 |
+
}
|