41 lines
1.1 KiB
Markdown
41 lines
1.1 KiB
Markdown
|
---
|
||
|
|
license: mit
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- llama
|
||
|
|
- historical
|
||
|
|
- causal-lm
|
||
|
|
- mlx
|
||
|
|
- mlx-my-repo
|
||
|
|
base_model: haykgrigorian/TimeCapsuleLLM-v2-1800-1875
|
||
|
|
---
|
||
|
|
|
||
|
|
# FractalSurfer/TimeCapsuleLLM-v2-1800-1875-mlx-fp16
|
||
|
|
|
||
|
|
The Model [FractalSurfer/TimeCapsuleLLM-v2-1800-1875-mlx-fp16](https://huggingface.co/FractalSurfer/TimeCapsuleLLM-v2-1800-1875-mlx-fp16) was converted to MLX format from [haykgrigorian/TimeCapsuleLLM-v2-1800-1875](https://huggingface.co/haykgrigorian/TimeCapsuleLLM-v2-1800-1875) using mlx-lm version **0.29.1**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("FractalSurfer/TimeCapsuleLLM-v2-1800-1875-mlx-fp16")
|
||
|
|
|
||
|
|
prompt="hello"
|
||
|
|
|
||
|
|
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
||
|
|
messages = [{"role": "user", "content": prompt}]
|
||
|
|
prompt = tokenizer.apply_chat_template(
|
||
|
|
messages, tokenize=False, add_generation_prompt=True
|
||
|
|
)
|
||
|
|
|
||
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||
|
|
```
|