Instructions to use mlx-community/zephyr-7b-beta-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/zephyr-7b-beta-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/zephyr-7b-beta-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/zephyr-7b-beta-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/zephyr-7b-beta-4bit" --prompt "Once upon a time"
Commit ·
c90dcd5
1
Parent(s): 9aad755
Add `weights.npz` and `config.json`
Browse files- config.json +16 -0
- weights.npz +3 -0
config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_layers": 32,
|
| 3 |
+
"dim": 4096,
|
| 4 |
+
"hidden_dim": 14336,
|
| 5 |
+
"n_heads": 32,
|
| 6 |
+
"head_dim": 128,
|
| 7 |
+
"n_kv_heads": 8,
|
| 8 |
+
"norm_eps": 1e-05,
|
| 9 |
+
"vocab_size": 32000,
|
| 10 |
+
"sliding_window": 4096,
|
| 11 |
+
"quantization_config": {
|
| 12 |
+
"group_size": 64,
|
| 13 |
+
"bits": 4
|
| 14 |
+
},
|
| 15 |
+
"model_type": "mistral"
|
| 16 |
+
}
|
weights.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5fbab5868959a9e9a90ddc059685e26cd72eaabd91cc689e77c95f76f1a1534
|
| 3 |
+
size 4969570716
|