7.7 GB
10 files
Updated 2 months ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.52 kB xet | 818ba6de | |
| README.md | 933 Bytes xet | 6df700f2 | |
| config.json | 794 Bytes xet | 91a4be88 | |
| model-00001-of-00002.safetensors | 5.34 GB xet | a920a8b0 | |
| model-00002-of-00002.safetensors | 2.35 GB xet | 4bd3755a | |
| model.safetensors.index.json | 63.5 kB xet | 1f9aae43 | |
| special_tokens_map.json | 414 Bytes xet | 23c80080 | |
| tokenizer.json | 3.51 MB xet | cb4232ea | |
| tokenizer.model | 493 kB xet | 1e090c2d | |
| tokenizer_config.json | 995 Bytes xet | dd464c94 |
mlx-community/SakanaAI-EvoLLM-JP-v1-7B-8bit
The Model mlx-community/SakanaAI-EvoLLM-JP-v1-7B-8bit was converted to MLX format from SakanaAI/EvoLLM-JP-v1-7B using mlx-lm version 0.19.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/SakanaAI-EvoLLM-JP-v1-7B-8bit")
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)
- Total size
- 7.7 GB
- Files
- 10
- Last updated
- Jul 8
- Pre-warmed CDN
- US EU US EU