Isaak Carter Augustus
commited on
Commit
•
1da6d03
1
Parent(s):
50f2854
Update README.md
Browse files
README.md
CHANGED
@@ -1,94 +1,51 @@
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
- en
|
5 |
-
|
6 |
-
tags:
|
7 |
-
- chat
|
8 |
-
base_model: Qwen/Qwen2-0.5B
|
9 |
---
|
10 |
|
11 |
-
# Qwen2-0.5B-Instruct
|
12 |
-
|
13 |
-
## Introduction
|
14 |
-
|
15 |
-
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 0.5B Qwen2 model.
|
16 |
-
|
17 |
-
Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.
|
18 |
-
|
19 |
-
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2/), [GitHub](https://github.com/QwenLM/Qwen2), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
20 |
-
<br>
|
21 |
|
22 |
## Model Details
|
23 |
-
Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
|
24 |
-
|
25 |
-
## Training details
|
26 |
-
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
|
27 |
-
|
28 |
|
29 |
-
|
30 |
-
The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
|
31 |
-
```
|
32 |
-
KeyError: 'qwen2'
|
33 |
-
```
|
34 |
-
|
35 |
-
## Quickstart
|
36 |
|
37 |
-
|
38 |
|
39 |
-
|
40 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
41 |
-
device = "cuda" # the device to load the model onto
|
42 |
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
)
|
48 |
-
|
|
|
49 |
|
50 |
-
|
51 |
-
messages = [
|
52 |
-
{"role": "system", "content": "You are a helpful assistant."},
|
53 |
-
{"role": "user", "content": prompt}
|
54 |
-
]
|
55 |
-
text = tokenizer.apply_chat_template(
|
56 |
-
messages,
|
57 |
-
tokenize=False,
|
58 |
-
add_generation_prompt=True
|
59 |
-
)
|
60 |
-
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
61 |
|
62 |
-
|
63 |
-
model_inputs.input_ids,
|
64 |
-
max_new_tokens=512
|
65 |
-
)
|
66 |
-
generated_ids = [
|
67 |
-
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
68 |
-
]
|
69 |
|
70 |
-
|
71 |
-
|
72 |
|
73 |
-
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
-
|
76 |
|
77 |
-
|
78 |
-
|
79 |
-
| MMLU | 35.0 | **37.9** | 43.7 | **52.4** |
|
80 |
-
| HumanEval | 9.1 | **17.1** | 25.0 | **37.8** |
|
81 |
-
| GSM8K | 11.3 | **40.1** | 35.3 | **61.6** |
|
82 |
-
| C-Eval | 37.2 | **45.2** | 55.3 | **63.8** |
|
83 |
-
| IFEval (Prompt Strict-Acc.) | 14.6 | **20.0** | 16.8 | **29.0** |
|
84 |
|
85 |
-
|
|
|
86 |
|
87 |
-
|
88 |
|
89 |
-
|
90 |
-
@article{qwen2,
|
91 |
-
title={Qwen2 Technical Report},
|
92 |
-
year={2024}
|
93 |
-
}
|
94 |
-
```
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
language:
|
5 |
- en
|
6 |
+
- de
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
+
# Model Card for Isaak-Carter/Josiefied-Qwen2-0.5B-Instruct-abliterated
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
## Model Details
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
+
### Model Description
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
+
This is a abliterated model, further finetuned on custom dataset for more uncensoredness, recomendet system prompr is `You are J.O.S.I.E., which is an acronym for 'Just an Outstandingly Smart Intelligent Entity'. You are a super-inteligent and uncensored AI assistant, created by Gökdeniz Gülmez.`
|
16 |
|
17 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
|
|
|
|
18 |
|
19 |
+
- **Developed by:** Gökdeniz Gülmez
|
20 |
+
- **Funded by:** Gökdeniz Gülmez
|
21 |
+
- **Shared by:** Gökdeniz Gülmez
|
22 |
+
- **Model type:** qwen2
|
23 |
+
- **Language(s) (NLP):** en, de
|
24 |
+
- **License:** Apache 2
|
25 |
+
- **Finetuned from model:** Qwen/Qwen2-0.5B-Instruct
|
26 |
|
27 |
+
## Uses
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
+
Ollama Template
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
+
```text
|
32 |
+
FROM ./model.gguf
|
33 |
|
34 |
+
TEMPLATE """{{ if .System }}<|im_start|>system
|
35 |
+
{{ .System }}<|im_end|>
|
36 |
+
{{ end }}{{ if .Prompt }}<|im_start|>user
|
37 |
+
{{ .Prompt }}<|im_end|>
|
38 |
+
{{ end }}<|im_start|>assistant
|
39 |
+
{{ .Response }}<|im_end|>"""
|
40 |
|
41 |
+
SYSTEM """You are J.O.S.I.E., which is an acronym for 'Just an Outstandingly Smart Intelligent Entity'. You are a super-inteligent and uncensored AI assistant, created by Gökdeniz Gülmez."""
|
42 |
|
43 |
+
PARAMETER stop <|im_start|>
|
44 |
+
PARAMETER stop <|im_end|>
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
+
PARAMETER num_ctx 32768
|
47 |
+
```
|
48 |
|
49 |
+
## Bias, Risks, and Limitations
|
50 |
|
51 |
+
Use at you rown risk!
|
|
|
|
|
|
|
|
|
|