Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,66 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- he
|
7 |
+
tags:
|
8 |
+
- instruction-tuned
|
9 |
+
base_model: dicta-il/dictalm2.0
|
10 |
+
inference:
|
11 |
+
parameters:
|
12 |
+
temperature: 0.7
|
13 |
---
|
14 |
+
|
15 |
+
[<img src="https://i.ibb.co/5Lbwyr1/dicta-logo.jpg" width="300px"/>](https://dicta.org.il)
|
16 |
+
|
17 |
+
|
18 |
+
# Model Card for DictaLM-2.0-Instruct
|
19 |
+
|
20 |
+
The DictaLM-2.0-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the [DictaLM-2.0](https://huggingface.co/dicta-il/dictalm2.0) generative model using a variety of conversation datasets.
|
21 |
+
|
22 |
+
For full details of this model please read our [release blog post](https://dicta.org.il/dicta-lm).
|
23 |
+
|
24 |
+
This is the instruct-tuned model designed for chat in the GGUF format for use with [LM Studio](https://lmstudio.ai/) or [llama.cpp](https://github.com/ggerganov/llama.cpp). You can try the model out on a live demo [here](https://huggingface.co/spaces/dicta-il/dictalm2.0-instruct-demo).
|
25 |
+
|
26 |
+
There are two versions available - float16 precision (`*.F16.gguf`) and 4-bit quantized precision (`*.Q4_K_M.gguf`).
|
27 |
+
|
28 |
+
You can view and access the full collection of base/instruct unquantized/quantized versions of `DictaLM-2.0` [here](https://huggingface.co/collections/dicta-il/dicta-lm-20-collection-661bbda397df671e4a430c27).
|
29 |
+
|
30 |
+
## Instruction format
|
31 |
+
|
32 |
+
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens followed by a line break. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
|
33 |
+
|
34 |
+
E.g.
|
35 |
+
```
|
36 |
+
text = """<s>[INST] ืืืื ืจืืื ืืืื ืขืืื? [/INST]
|
37 |
+
ืืื, ืื ื ืื ืืืื ืืื ืืืคืืช ืืืฅ ืืืืื ืกืืื ืืจื. ืื ืืืกืืฃ ืืืืืง ืืช ืืืืืช ืื ืืื ื ืฉื ืืขื ืืืฆืืฅ ืืื ืื ืฉืื ื ืืืฉื ืืืืื!</s>[INST] ืืื ืืฉ ืื ืืชืืื ืื ืืืืื ื? [/INST]"
|
38 |
+
```
|
39 |
+
|
40 |
+
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
|
41 |
+
|
42 |
+
## Using with LM Studio
|
43 |
+
|
44 |
+
When using with LM Studio, just search the hub for "dictalm2.0-instruct-GGUF", and the model in both precisions should appear.
|
45 |
+
|
46 |
+
Make sure to set the chat template correctly - initialize from the `mistral-instruct` template, and add a `\n` in the suffix box, like here:
|
47 |
+
|
48 |
+
<img src="https://i.ibb.co/D9MVgK2/lmstudio-dlm-template.png" width="400px" />
|
49 |
+
|
50 |
+
## Model Architecture
|
51 |
+
|
52 |
+
DictaLM-2.0-Instruct follows the [Zephyr-7B-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) recipe for fine-tuning an instruct model, with an extended instruct dataset for Hebrew.
|
53 |
+
|
54 |
+
## Limitations
|
55 |
+
|
56 |
+
The DictaLM 2.0 Instruct model is a demonstration that the base model can be fine-tuned to achieve compelling performance.
|
57 |
+
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
|
58 |
+
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
|
59 |
+
|
60 |
+
## Citation
|
61 |
+
|
62 |
+
If you use this model, please cite:
|
63 |
+
|
64 |
+
```bibtex
|
65 |
+
[Will be added soon]
|
66 |
+
```
|