50 lines
1.4 KiB
Markdown
50 lines
1.4 KiB
Markdown
|
---
|
||
|
|
base_model: remyxai/stablelm-zephyr-3B_localmentor
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- stablelm
|
||
|
|
- zephyr
|
||
|
|
- gguf
|
||
|
|
library_name: llama.cpp
|
||
|
|
model_creator: remyxai
|
||
|
|
model_name: stablelm-zephyr-3B_localmentor
|
||
|
|
model_type: stablelm
|
||
|
|
prompt_template: |
|
||
|
|
<|system|>
|
||
|
|
{system_prompt}</s>
|
||
|
|
<|user|>
|
||
|
|
{prompt}</s>
|
||
|
|
<|assistant|>
|
||
|
|
quantized_by: mgonzs13
|
||
|
|
---
|
||
|
|
|
||
|
|
# stablelm-zephyr-3B-localmentor-GGUF
|
||
|
|
|
||
|
|
**Model creator:** [remyxai](https://huggingface.co/remyxai)<br>
|
||
|
|
**Original model**: [stablelm-zephyr-3B_localmentor](https://huggingface.co/remyxai/stablelm-zephyr-3B_localmentor)<br>
|
||
|
|
**GGUF quantization:** `llama.cpp` commit [fadde6713506d9e6c124f5680ab8c7abebe31837](https://github.com/ggerganov/llama.cpp/tree/fadde6713506d9e6c124f5680ab8c7abebe31837)<br>
|
||
|
|
|
||
|
|
## Description
|
||
|
|
|
||
|
|
Fine-tune with low-rank adapters on 25K conversational turns discussing tech/startup from over 800 podcast episodes.
|
||
|
|
|
||
|
|
- **Developed by:** [Remyx.AI](https://huggingface.co/remyxai)
|
||
|
|
- **License:** apache-2.0
|
||
|
|
- **Finetuned from model:** [stablelm-zephyr-3b](https://huggingface.co/stabilityai/stablelm-zephyr-3b)
|
||
|
|
- **Repository**: https://github.com/remyxai/LocalMentor
|
||
|
|
|
||
|
|
## Prompt Template
|
||
|
|
|
||
|
|
Following the [tokenizer_config.json](https://huggingface.co/remyxai/stablelm-zephyr-3B_localmentor/blob/main/tokenizer_config.json), the prompt template is Zephyr.
|
||
|
|
|
||
|
|
```
|
||
|
|
<|system|>
|
||
|
|
{system_prompt}</s>
|
||
|
|
<|user|>
|
||
|
|
{prompt}</s>
|
||
|
|
<|assistant|>
|
||
|
|
```
|