Update README.md
Browse files
README.md
CHANGED
@@ -1,201 +1,154 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
|
|
5 |
|
6 |
-
|
7 |
|
8 |
-
|
9 |
|
|
|
10 |
|
|
|
11 |
|
12 |
-
## Model Details
|
13 |
-
|
14 |
-
### Model Description
|
15 |
-
|
16 |
-
<!-- Provide a longer summary of what this model is. -->
|
17 |
-
|
18 |
-
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
-
|
20 |
-
- **Developed by:** [More Information Needed]
|
21 |
-
- **Funded by [optional]:** [More Information Needed]
|
22 |
-
- **Shared by [optional]:** [More Information Needed]
|
23 |
-
- **Model type:** [More Information Needed]
|
24 |
-
- **Language(s) (NLP):** [More Information Needed]
|
25 |
-
- **License:** [More Information Needed]
|
26 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
-
|
28 |
-
### Model Sources [optional]
|
29 |
-
|
30 |
-
<!-- Provide the basic links for the model. -->
|
31 |
-
|
32 |
-
- **Repository:** [More Information Needed]
|
33 |
-
- **Paper [optional]:** [More Information Needed]
|
34 |
-
- **Demo [optional]:** [More Information Needed]
|
35 |
-
|
36 |
-
## Uses
|
37 |
-
|
38 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
-
|
40 |
-
### Direct Use
|
41 |
-
|
42 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
-
|
44 |
-
[More Information Needed]
|
45 |
-
|
46 |
-
### Downstream Use [optional]
|
47 |
-
|
48 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
-
|
52 |
-
### Out-of-Scope Use
|
53 |
-
|
54 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
-
|
56 |
-
[More Information Needed]
|
57 |
-
|
58 |
-
## Bias, Risks, and Limitations
|
59 |
-
|
60 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
-
|
62 |
-
[More Information Needed]
|
63 |
-
|
64 |
-
### Recommendations
|
65 |
-
|
66 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
-
|
68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
-
|
70 |
-
## How to Get Started with the Model
|
71 |
-
|
72 |
-
Use the code below to get started with the model.
|
73 |
-
|
74 |
-
[More Information Needed]
|
75 |
-
|
76 |
-
## Training Details
|
77 |
-
|
78 |
-
### Training Data
|
79 |
-
|
80 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
-
|
82 |
-
[More Information Needed]
|
83 |
-
|
84 |
-
### Training Procedure
|
85 |
-
|
86 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
-
|
88 |
-
#### Preprocessing [optional]
|
89 |
-
|
90 |
-
[More Information Needed]
|
91 |
-
|
92 |
-
|
93 |
-
#### Training Hyperparameters
|
94 |
-
|
95 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
-
|
97 |
-
#### Speeds, Sizes, Times [optional]
|
98 |
-
|
99 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
-
|
101 |
-
[More Information Needed]
|
102 |
-
|
103 |
-
## Evaluation
|
104 |
|
105 |
-
|
|
|
106 |
|
107 |
-
|
|
|
|
|
|
|
|
|
|
|
108 |
|
109 |
-
|
|
|
|
|
|
|
|
|
|
|
110 |
|
111 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
|
113 |
-
|
|
|
114 |
|
115 |
-
#### Factors
|
116 |
-
|
117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Metrics
|
122 |
-
|
123 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
-
|
125 |
-
[More Information Needed]
|
126 |
-
|
127 |
-
### Results
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Summary
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
## Model Examination [optional]
|
136 |
-
|
137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
-
|
155 |
-
### Model Architecture and Objective
|
156 |
-
|
157 |
-
[More Information Needed]
|
158 |
-
|
159 |
-
### Compute Infrastructure
|
160 |
-
|
161 |
-
[More Information Needed]
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
## Model Card Contact
|
198 |
-
|
199 |
-
[More Information Needed]
|
200 |
|
|
|
201 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
datasets:
|
3 |
+
- HuggingFaceH4/ultrachat_200k
|
4 |
+
- allenai/ultrafeedback_binarized_cleaned
|
5 |
+
- meta-math/MetaMathQA
|
6 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
7 |
+
- openchat/openchat_sharegpt4_dataset
|
8 |
+
- LDJnr/Capybara
|
9 |
+
- Intel/orca_dpo_pairs
|
10 |
+
- hkust-nlp/deita-10k-v0
|
11 |
+
- teknium/OpenHermes-2.5
|
12 |
+
|
13 |
+
language:
|
14 |
+
- en
|
15 |
+
tags:
|
16 |
+
- causal-lm
|
17 |
+
extra_gated_fields:
|
18 |
+
Name: text
|
19 |
+
Email: text
|
20 |
+
Country: text
|
21 |
+
Organization or Affiliation: text
|
22 |
+
I ALLOW Stability AI to email me about new model releases: checkbox
|
23 |
+
license: other
|
24 |
---
|
25 |
+
# `StableLM 2 Chat 1.6B`
|
26 |
|
27 |
+
## Model Description
|
28 |
|
29 |
+
`Stable LM 2 Chat 1.6B` is a 1.6 billion parameter instruction tuned language model inspired by [HugginFaceH4's Zephyr 7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) training pipeline. The model is trained on a mix of publicly available datasets and synthetic datasets, utilizing [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290).
|
30 |
|
31 |
+
## Usage
|
32 |
|
33 |
+
`StableLM 2 1.6B Chat` uses the following ChatML format:
|
34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
+
```python
|
37 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
38 |
|
39 |
+
tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-2-1_6b-chat')
|
40 |
+
model = AutoModelForCausalLM.from_pretrained(
|
41 |
+
'stabilityai/stablelm-2-1_6b-chat',
|
42 |
+
device_map="auto",
|
43 |
+
trust_remote_code=True,
|
44 |
+
)
|
45 |
|
46 |
+
prompt = [{'role': 'user', 'content': 'Implement snake game using pygame'}]
|
47 |
+
inputs = tokenizer.apply_chat_template(
|
48 |
+
prompt,
|
49 |
+
add_generation_prompt=True,
|
50 |
+
return_tensors='pt'
|
51 |
+
)
|
52 |
|
53 |
+
tokens = model.generate(
|
54 |
+
inputs.to(model.device),
|
55 |
+
max_new_tokens=100,
|
56 |
+
temperature=0.7,
|
57 |
+
do_sample=True
|
58 |
+
)
|
59 |
+
output = tokenizer.decode(tokens[:, inputs.shape[-1]:][0], skip_special_tokens=False)
|
60 |
|
61 |
+
print(output)
|
62 |
+
```
|
63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
+
## Model Details
|
66 |
|
67 |
+
* **Developed by**: [Stability AI](https://stability.ai/)
|
68 |
+
* **Model type**: `StableLM 2 Chat 1.6B` model is an auto-regressive language model based on the transformer decoder architecture.
|
69 |
+
* **Language(s)**: English
|
70 |
+
* **Paper**: [Stable LM 2 1.6B Technical Report](https://drive.google.com/file/d/1JYJHszhS8EFChTbNAf8xmqhKjogWRrQF/view?usp=sharing)
|
71 |
+
* **Library**: [Alignment Handbook](https://github.com/huggingface/alignment-handbook.git)
|
72 |
+
* **Finetuned from model**: [https://huggingface.co/stabilityai/stablelm-2-1_6b](https://huggingface.co/stabilityai/stablelm-2-1_6b)
|
73 |
+
* **License**: [StabilityAI Non-Commercial Research Community License](https://huggingface.co/stabilityai/stablelm-2-1_6b-chat/blob/main/LICENSE). If you want to use this model for your commercial products or purposes, please contact us [here](https://stability.ai/contact) to learn more.
|
74 |
+
* **Contact**: For questions and comments about the model, please email `lm@stability.ai`
|
75 |
+
|
76 |
+
### Training Dataset
|
77 |
+
|
78 |
+
The dataset is comprised of a mixture of open datasets large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets):
|
79 |
+
1. SFT Datasets
|
80 |
+
- HuggingFaceH4/ultrachat_200k
|
81 |
+
- meta-math/MetaMathQA
|
82 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
83 |
+
- Open-Orca/SlimOrca
|
84 |
+
- openchat/openchat_sharegpt4_dataset
|
85 |
+
- LDJnr/Capybara
|
86 |
+
- hkust-nlp/deita-10k-v0
|
87 |
+
- teknium/OpenHermes-2.5
|
88 |
+
|
89 |
+
2. Preference Datasets:
|
90 |
+
- allenai/ultrafeedback_binarized_cleaned
|
91 |
+
- Intel/orca_dpo_pairs
|
92 |
+
- argilla/dpo-mix-7k
|
93 |
+
|
94 |
+
## Performance
|
95 |
+
|
96 |
+
### MT-Bench
|
97 |
+
|
98 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/61b2bf4f5b1f7cad1799cfbb/QH00HVM3lg-5f17U_py4K.png" alt="mt_bench_plot" width="600"/>
|
99 |
+
|
100 |
+
| Model | Size | MT-Bench |
|
101 |
+
|-------------------------|------|----------|
|
102 |
+
| Mistral-7B-Instruct-v0.2| 7B | 7.61 |
|
103 |
+
| Llama2-Chat | 70B | 6.86 |
|
104 |
+
| stablelm-zephyr-3b | 3B | 6.64 |
|
105 |
+
| MPT-30B-Chat | 30B | 6.39 |
|
106 |
+
| **stablelm-2-1_6b-chat** | 1.6B | 5.83 |
|
107 |
+
| stablelm-2-zephyr-1.6b | 1.6B | 5.42 |
|
108 |
+
| Falcon-40B-Instruct | 40B | 5.17 |
|
109 |
+
| Qwen-1.8B-Chat | 1.8B | 4.95 |
|
110 |
+
| dolphin-2.6-phi-2 | 2.7B | 4.93 |
|
111 |
+
| phi-2 | 2.7B | 4.29 |
|
112 |
+
| TinyLlama-1.1B-Chat-v1.0| 1.1B | 3.46 |
|
113 |
+
|
114 |
+
### OpenLLM Leaderboard
|
115 |
+
|
116 |
+
| Model | Size | Average | ARC Challenge (acc_norm) | HellaSwag (acc_norm) | MMLU (acc_norm) | TruthfulQA (mc2) | Winogrande (acc) | Gsm8k (acc) |
|
117 |
+
|----------------------------------------|------|---------|-------------------------|----------------------|-----------------|------------------|------------------|-------------|
|
118 |
+
| microsoft/phi-2 | 2.7B | 61.32% | 61.09% | 75.11% | 58.11% | 44.47% | 74.35% | 54.81% |
|
119 |
+
| **stabilityai/stablelm-2-1_6b-chat** | 1.6B | 50.80% | 43.94% | 69.22% | 41.59% | 46.52% | 64.56 | 38.96 |
|
120 |
+
| stabilityai/stablelm-2-zephyr-1_6b | 1.6B | 49.89% | 43.69% | 69.34% | 41.85% | 45.21% | 64.09% | 35.18% |
|
121 |
+
| microsoft/phi-1_5 | 1.3B | 47.69% | 52.90% | 63.79% | 43.89% | 40.89% | 72.22% | 12.43% |
|
122 |
+
| stabilityai/stablelm-2-1_6b | 1.6B | 45.54% | 43.43% | 70.49% | 38.93% | 36.65% | 65.90% | 17.82% |
|
123 |
+
| mosaicml/mpt-7b | 7B | 44.28% | 47.70% | 77.57% | 30.80% | 33.40% | 72.14% | 4.02% |
|
124 |
+
| KnutJaegersberg/Qwen-1_8B-Llamaified* | 1.8B | 44.75% | 37.71% | 58.87% | 46.37% | 39.41% | 61.72% | 24.41% |
|
125 |
+
| openlm-research/open_llama_3b_v2 | 3B | 40.28% | 40.27% | 71.60% | 27.12% | 34.78% | 67.01% | 0.91% |
|
126 |
+
| iiuae/falcon-rw-1b | 1B | 37.07% | 35.07% | 63.56% | 25.28% | 35.96% | 62.04% | 0.53% |
|
127 |
+
| TinyLlama/TinyLlama-1.1B-3T | 1.1B | 36.40% | 33.79% | 60.31% | 26.04% | 37.32% | 59.51% | 1.44% |
|
128 |
+
|
129 |
+
|
130 |
+
## Use and Limitations
|
131 |
+
|
132 |
+
### Intended Use
|
133 |
+
|
134 |
+
The model is intended to be used in chat-like applications. Developers must evaluate the model for safety performance in their specific use case. Read more about [safety and limitations](#limitations-and-bias) below.
|
135 |
+
|
136 |
+
### Limitations and Bias
|
137 |
+
|
138 |
+
This model is not trained against adversarial inputs. We strongly recommend pairing this model with an input and output classifier to prevent harmful responses.
|
139 |
+
|
140 |
+
Through our internal red teaming, we discovered that while the model will not output harmful information if not prompted to do so, it will hallucinate many facts. It is also willing to output potentially harmful outputs or misinformation when the user requests it.
|
141 |
+
Using this model will require guardrails around your inputs and outputs to ensure that any outputs returned are not misinformation or harmful.
|
142 |
+
Additionally, as each use case is unique, we recommend running your own suite of tests to ensure proper performance of this model.
|
143 |
+
Finally, do not use the models if they are unsuitable for your application, or for any applications that may cause deliberate or unintentional harm to others.
|
144 |
+
|
145 |
+
|
146 |
+
## How to Cite
|
147 |
+
|
148 |
+
```bibtex
|
149 |
+
@misc{StableLM-2-1.6B,
|
150 |
+
url={[https://huggingface.co/stabilityai/stablelm-2-1.6b](https://huggingface.co/stabilityai/stablelm-2-1.6b)},
|
151 |
+
title={Stable LM 2 1.6B},
|
152 |
+
author={Stability AI Language Team}
|
153 |
+
}
|
154 |
+
```
|