75 lines
3.0 KiB
Markdown
75 lines
3.0 KiB
Markdown
---
|
|
base_model: Felladrin/llama2_xs_460M_experimental_evol_instruct
|
|
datasets:
|
|
- KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format
|
|
inference: false
|
|
model_creator: Felladrin
|
|
model_name: llama2_xs_460M_experimental_evol_instruct
|
|
pipeline_tag: text-generation
|
|
quantized_by: afrideva
|
|
tags:
|
|
- autotrain
|
|
- text-generation
|
|
- gguf
|
|
- ggml
|
|
- quantized
|
|
- q2_k
|
|
- q3_k_m
|
|
- q4_k_m
|
|
- q5_k_m
|
|
- q6_k
|
|
- q8_0
|
|
widget:
|
|
- text: '### Instruction:
|
|
|
|
Find me a list of some nice places to visit around the world.
|
|
|
|
|
|
### Response:'
|
|
- text: '### Instruction:
|
|
|
|
Tell me all you know about the Earth.
|
|
|
|
|
|
### Response:'
|
|
---
|
|
# Felladrin/llama2_xs_460M_experimental_evol_instruct-GGUF
|
|
|
|
Quantized GGUF model files for [llama2_xs_460M_experimental_evol_instruct](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_evol_instruct) from [Felladrin](https://huggingface.co/Felladrin)
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q2_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q2_k.gguf) | q2_k | 212.56 MB |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q3_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q3_k_m.gguf) | q3_k_m | 238.87 MB |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q4_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q4_k_m.gguf) | q4_k_m | 288.52 MB |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q5_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q5_k_m.gguf) | q5_k_m | 333.29 MB |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q6_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q6_k.gguf) | q6_k | 380.87 MB |
|
|
| [llama2_xs_460m_experimental_evol_instruct.q8_0.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_evol_instruct-GGUF/resolve/main/llama2_xs_460m_experimental_evol_instruct.q8_0.gguf) | q8_0 | 492.67 MB |
|
|
|
|
|
|
|
|
## Original Model Card:
|
|
# ahxt's llama2_xs_460M_experimental trained on the WizardLM's Evol Instruct dataset using AutoTrain
|
|
|
|
- Base model: [ahxt/llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental)
|
|
- Dataset: [KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format](https://huggingface.co/datasets/KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format)
|
|
- Training: 13.5h under [these parameters](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_evol_instruct/blob/cc151c5669ea37c3ef972e375c74f2d9bfd92b49/training_params.json)
|
|
|
|
## Recommended Prompt Format
|
|
|
|
```
|
|
### Instruction:
|
|
<instruction>
|
|
|
|
### Response:
|
|
```
|
|
|
|
## Recommended Inference Parameters
|
|
|
|
```yml
|
|
repetition_penalty: 1.15
|
|
do_sample: true
|
|
temperature: 0.5
|
|
top_p: 0.5
|
|
``` |