Hugging Face's logo

afrideva
/
tau-0.5B-GGUF

Text Generation
GGUF
English
Chinese
ggml
quantized
q2_k
q3_k_m
q4_k_m
q5_k_m
q6_k
q8_0
Model card Files Community
afrideva commited on
Commit
388a0e8
•
1 Parent(s): e19175e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +179 -0
README.md ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: M4-ai/tau-0.5B
3
+ datasets:
4
+ - Locutusque/UltraTextbooks-2.0
5
+ inference: false
6
+ language:
7
+ - en
8
+ - zh
9
+ license: other
10
+ model_creator: M4-ai
11
+ model_name: tau-0.5B
12
+ pipeline_tag: text-generation
13
+ quantized_by: afrideva
14
+ tags:
15
+ - gguf
16
+ - ggml
17
+ - quantized
18
+ - q2_k
19
+ - q3_k_m
20
+ - q4_k_m
21
+ - q5_k_m
22
+ - q6_k
23
+ - q8_0
24
+ ---
25
+ # M4-ai/tau-0.5B-GGUF
26
+
27
+ Quantized GGUF model files for [tau-0.5B](https://huggingface.co/M4-ai/tau-0.5B) from [M4-ai](https://huggingface.co/M4-ai)
28
+
29
+
30
+ | Name | Quant method | Size |
31
+ | ---- | ---- | ---- |
32
+ | [tau-0.5b.fp16.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.fp16.gguf) | fp16 | 1.25 GB |
33
+ | [tau-0.5b.q2_k.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q2_k.gguf) | q2_k | 298.41 MB |
34
+ | [tau-0.5b.q3_k_m.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q3_k_m.gguf) | q3_k_m | 349.88 MB |
35
+ | [tau-0.5b.q4_k_m.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q4_k_m.gguf) | q4_k_m | 407.16 MB |
36
+ | [tau-0.5b.q5_k_m.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q5_k_m.gguf) | q5_k_m | 459.24 MB |
37
+ | [tau-0.5b.q6_k.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q6_k.gguf) | q6_k | 514.58 MB |
38
+ | [tau-0.5b.q8_0.gguf](https://huggingface.co/afrideva/tau-0.5B-GGUF/resolve/main/tau-0.5b.q8_0.gguf) | q8_0 | 664.60 MB |
39
+
40
+
41
+
42
+ ## Original Model Card:
43
+ # tau-0.5B
44
+
45
+ ## Model Details
46
+ - **Model Name:** tau-0.5B
47
+ - **Base Model:** Qwen1.5-0.5B
48
+ - **Dataset:** UltraTextbooks-2.0
49
+ - **Model Size:** 0.5B parameters
50
+ - **Model Type:** Language Model
51
+ - **Training Procedure:** Further pre-training of Qwen1.5-0.5B on UltraTextbooks-2.0.
52
+
53
+ ## Model Use
54
+ tau-0.5B is designed to be a general-purpose language model with enhanced capabilities in the domains of machine learning, mathematics, and coding. It can be used for a wide range of natural language processing tasks, such as:
55
+ - Educational question answering
56
+ - Text summarization
57
+ - Content generation for educational purposes
58
+ - Code understanding and generation
59
+ - Mathematical problem solving
60
+
61
+ The model's exposure to the diverse content in the UltraTextbooks-2.0 dataset makes it particularly well-suited for applications in educational technology and research.
62
+
63
+ ## Training Data
64
+ tau-0.5B was further pre-trained on the UltraTextbooks-2.0 dataset, which is an expanded version of the original UltraTextbooks dataset. UltraTextbooks-2.0 incorporates additional high-quality synthetic and human-written textbooks from various sources on the Hugging Face platform, with a focus on increasing the diversity of content in the domains of machine learning, mathematics, and coding.
65
+
66
+ For more details on the dataset, please refer to the [UltraTextbooks-2.0 Dataset Card](https://huggingface.co/datasets/Locutusque/UltraTextbooks-2.0).
67
+
68
+ ## Performance and Limitations
69
+ Refer to [Evaluation](##Evaluation) for evaluations. It is essential to note that the model may still exhibit biases or inaccuracies present in the training data. Users are encouraged to critically evaluate the model's outputs and report any issues to facilitate continuous improvement.
70
+
71
+ ## Environmental Impact
72
+ The training of tau-0.5B required computational resources that contribute to the model's overall environmental impact. However, efforts were made to optimize the training process and minimize the carbon footprint.
73
+
74
+ ## Ethical Considerations
75
+ tau-0.5B was trained on a diverse dataset that may contain biases and inaccuracies. Users should be aware of these potential limitations and use the model responsibly. The model should not be used for tasks that could cause harm or discriminate against individuals or groups.
76
+
77
+ ## Evaluation
78
+
79
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
80
+ |---------------------------------|-------|------|-----:|--------|-----:|---|-----:|
81
+ |agieval_nous |N/A |none | 0|acc |0.2235|± |0.0434|
82
+ | | |none | 0|acc_norm|0.2141|± |0.0498|
83
+ | - agieval_aqua_rat | 1|none | 0|acc |0.1417|± |0.0219|
84
+ | | |none | 0|acc_norm|0.1535|± |0.0227|
85
+ | - agieval_logiqa_en | 1|none | 0|acc |0.2796|± |0.0176|
86
+ | | |none | 0|acc_norm|0.3118|± |0.0182|
87
+ | - agieval_lsat_ar | 1|none | 0|acc |0.2000|± |0.0264|
88
+ | | |none | 0|acc_norm|0.1696|± |0.0248|
89
+ | - agieval_lsat_lr | 1|none | 0|acc |0.2275|± |0.0186|
90
+ | | |none | 0|acc_norm|0.2020|± |0.0178|
91
+ | - agieval_lsat_rc | 1|none | 0|acc |0.1487|± |0.0217|
92
+ | | |none | 0|acc_norm|0.1561|± |0.0222|
93
+ | - agieval_sat_en | 1|none | 0|acc |0.2330|± |0.0295|
94
+ | | |none | 0|acc_norm|0.2039|± |0.0281|
95
+ | - agieval_sat_en_without_passage| 1|none | 0|acc |0.2524|± |0.0303|
96
+ | | |none | 0|acc_norm|0.1942|± |0.0276|
97
+ | - agieval_sat_math | 1|none | 0|acc |0.2227|± |0.0281|
98
+ | | |none | 0|acc_norm|0.1682|± |0.0253|
99
+
100
+ | Tasks |Version| Filter |n-shot| Metric |Value | |Stderr|
101
+ |---------------------------------------|-------|----------------|-----:|-----------|-----:|---|-----:|
102
+ |truthfulqa | 2|none | 0|acc |0.3931|± |0.0143|
103
+ |mmlu |N/A |none | 0|acc |0.3642|± |0.0040|
104
+ | - humanities |N/A |none | 5|acc |0.3320|± |0.0068|
105
+ | - formal_logic | 0|none | 5|acc |0.2619|± |0.0393|
106
+ | - high_school_european_history | 0|none | 5|acc |0.4909|± |0.0390|
107
+ | - high_school_us_history | 0|none | 5|acc |0.4167|± |0.0346|
108
+ | - high_school_world_history | 0|none | 5|acc |0.4641|± |0.0325|
109
+ | - international_law | 0|none | 5|acc |0.5537|± |0.0454|
110
+ | - jurisprudence | 0|none | 5|acc |0.4167|± |0.0477|
111
+ | - logical_fallacies | 0|none | 5|acc |0.2638|± |0.0346|
112
+ | - moral_disputes | 0|none | 5|acc |0.3757|± |0.0261|
113
+ | - moral_scenarios | 0|none | 5|acc |0.2402|± |0.0143|
114
+ | - philosophy | 0|none | 5|acc |0.3794|± |0.0276|
115
+ | - prehistory | 0|none | 5|acc |0.3426|± |0.0264|
116
+ | - professional_law | 0|none | 5|acc |0.3103|± |0.0118|
117
+ | - world_religions | 0|none | 5|acc |0.2807|± |0.0345|
118
+ | - other |N/A |none | 5|acc |0.4071|± |0.0088|
119
+ | - business_ethics | 0|none | 5|acc |0.4200|± |0.0496|
120
+ | - clinical_knowledge | 0|none | 5|acc |0.4491|± |0.0306|
121
+ | - college_medicine | 0|none | 5|acc |0.3873|± |0.0371|
122
+ | - global_facts | 0|none | 5|acc |0.3600|± |0.0482|
123
+ | - human_aging | 0|none | 5|acc |0.3498|± |0.0320|
124
+ | - management | 0|none | 5|acc |0.4854|± |0.0495|
125
+ | - marketing | 0|none | 5|acc |0.5470|± |0.0326|
126
+ | - medical_genetics | 0|none | 5|acc |0.4000|± |0.0492|
127
+ | - miscellaneous | 0|none | 5|acc |0.4291|± |0.0177|
128
+ | - nutrition | 0|none | 5|acc |0.4183|± |0.0282|
129
+ | - professional_accounting | 0|none | 5|acc |0.3582|± |0.0286|
130
+ | - professional_medicine | 0|none | 5|acc |0.3015|± |0.0279|
131
+ | - virology | 0|none | 5|acc |0.3494|± |0.0371|
132
+ | - social_sciences |N/A |none | 5|acc |0.4075|± |0.0088|
133
+ | - econometrics | 0|none | 5|acc |0.2719|± |0.0419|
134
+ | - high_school_geography | 0|none | 5|acc |0.5000|± |0.0356|
135
+ | - high_school_government_and_politics| 0|none | 5|acc |0.4611|± |0.0360|
136
+ | - high_school_macroeconomics | 0|none | 5|acc |0.4051|± |0.0249|
137
+ | - high_school_microeconomics | 0|none | 5|acc |0.3908|± |0.0317|
138
+ | - high_school_psychology | 0|none | 5|acc |0.4239|± |0.0212|
139
+ | - human_sexuality | 0|none | 5|acc |0.3893|± |0.0428|
140
+ | - professional_psychology | 0|none | 5|acc |0.3399|± |0.0192|
141
+ | - public_relations | 0|none | 5|acc |0.4455|± |0.0476|
142
+ | - security_studies | 0|none | 5|acc |0.3510|± |0.0306|
143
+ | - sociology | 0|none | 5|acc |0.5174|± |0.0353|
144
+ | - us_foreign_policy | 0|none | 5|acc |0.5500|± |0.0500|
145
+ | - stem |N/A |none | 5|acc |0.3276|± |0.0083|
146
+ | - abstract_algebra | 0|none | 5|acc |0.3000|± |0.0461|
147
+ | - anatomy | 0|none | 5|acc |0.2889|± |0.0392|
148
+ | - astronomy | 0|none | 5|acc |0.3487|± |0.0388|
149
+ | - college_biology | 0|none | 5|acc |0.3403|± |0.0396|
150
+ | - college_chemistry | 0|none | 5|acc |0.2600|± |0.0441|
151
+ | - college_computer_science | 0|none | 5|acc |0.3800|± |0.0488|
152
+ | - college_mathematics | 0|none | 5|acc |0.3300|± |0.0473|
153
+ | - college_physics | 0|none | 5|acc |0.2745|± |0.0444|
154
+ | - computer_security | 0|none | 5|acc |0.4300|± |0.0498|
155
+ | - conceptual_physics | 0|none | 5|acc |0.3447|± |0.0311|
156
+ | - electrical_engineering | 0|none | 5|acc |0.3931|± |0.0407|
157
+ | - elementary_mathematics | 0|none | 5|acc |0.3095|± |0.0238|
158
+ | - high_school_biology | 0|none | 5|acc |0.4161|± |0.0280|
159
+ | - high_school_chemistry | 0|none | 5|acc |0.2759|± |0.0314|
160
+ | - high_school_computer_science | 0|none | 5|acc |0.3100|± |0.0465|
161
+ | - high_school_mathematics | 0|none | 5|acc |0.3185|± |0.0284|
162
+ | - high_school_physics | 0|none | 5|acc |0.2517|± |0.0354|
163
+ | - high_school_statistics | 0|none | 5|acc |0.3009|± |0.0313|
164
+ | - machine_learning | 0|none | 5|acc |0.3036|± |0.0436|
165
+ |medqa_4options |Yaml |none | 5|acc |0.2687|± |0.0124|
166
+ | | |none | 5|acc_norm |0.2687|± |0.0124|
167
+ |logieval | 0|get-answer | 5|exact_match|0.3505|± |0.0120|
168
+ |gsm8k_cot | 3|strict-match | 8|exact_match|0.0690|± |0.0070|
169
+ | | |flexible-extract| 8|exact_match|0.1365|± |0.0095|
170
+
171
+
172
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
173
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
174
+ |arc_easy | 1|none | 25|acc |0.5981|± |0.0101|
175
+ | | |none | 25|acc_norm|0.5939|± |0.0101|
176
+ |arc_challenge| 1|none | 25|acc |0.2688|± |0.0130|
177
+ | | |none | 25|acc_norm|0.2969|± |0.0134|
178
+ ## Usage Rights
179
+ Make sure to read Qwen's license before using this model.