Instructions to use mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Add files using upload-large-folder tool
Browse files- README.md +1 -3
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
|
@@ -2,10 +2,10 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: deepseek-license
|
| 4 |
license_link: LICENSE
|
| 5 |
-
library_name: mlx
|
| 6 |
tags:
|
| 7 |
- mlx
|
| 8 |
pipeline_tag: text-generation
|
|
|
|
| 9 |
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
|
| 10 |
---
|
| 11 |
|
|
@@ -15,8 +15,6 @@ This model [mlx-community/deepseek-coder-v2-lite-instruct-4bit-awq](https://hugg
|
|
| 15 |
converted to MLX format from [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)
|
| 16 |
using mlx-lm version **0.25.2**.
|
| 17 |
|
| 18 |
-
AWQ Parameters: --bits 4 --group-size 64 --embed-bits 4 --embed-group-size 32 --num-samples 64 --sequence-length 512 --n-grid 50 with a customized calibration dataset
|
| 19 |
-
|
| 20 |
## Use with mlx
|
| 21 |
|
| 22 |
```bash
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: deepseek-license
|
| 4 |
license_link: LICENSE
|
|
|
|
| 5 |
tags:
|
| 6 |
- mlx
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
+
library_name: mlx
|
| 9 |
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
|
| 10 |
---
|
| 11 |
|
|
|
|
| 15 |
converted to MLX format from [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)
|
| 16 |
using mlx-lm version **0.25.2**.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Use with mlx
|
| 19 |
|
| 20 |
```bash
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5329652718
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:440437c26878ea85ab3a516caba412fd65cfa435daa2518328def367d1a0868d
|
| 3 |
size 5329652718
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3536651032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcb6f6494941ae0b2ed5fb5f55180dc3512b1e569cebd9dc10d9ad90da8409ab
|
| 3 |
size 3536651032
|