Text Generation
MLX
Safetensors
Polish
English
llama
apple-silicon
bielik
speakleash
polish
conversational
8-bit precision
Instructions to use agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit 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("agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit") 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 agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "agentGreg/Bielik-Minitron-7B-v3.0-Instruct-MLX-8bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
docs: fix benchmark repo link (matfiz -> agentGreg)
Browse files
README.md
CHANGED
|
@@ -71,7 +71,7 @@ Bielik-Minitron 7B został przetestowany na oficjalnym arkuszu CKE z **egzaminu
|
|
| 71 |
| 7 | Llama-PLLuM 8B | 3/30 (10%) |
|
| 72 |
| 7 | PLLuM 12B | 3/30 (10%) |
|
| 73 |
|
| 74 |
-
Pełna metodyka, kod, klucz odpowiedzi i analiza per-zadaniowa: [github.com/
|
| 75 |
|
| 76 |
## Atrybucja
|
| 77 |
|
|
@@ -99,4 +99,4 @@ Jeśli używasz tego modelu w pracy naukowej lub komercyjnej, cytuj oryginalny p
|
|
| 99 |
|
| 100 |
---
|
| 101 |
|
| 102 |
-
*Wagi MLX przygotowane w ramach benchmarku [Egzamin ósmoklasisty z matematyki 2026 — benchmark małych LLM-ów](https://github.com/
|
|
|
|
| 71 |
| 7 | Llama-PLLuM 8B | 3/30 (10%) |
|
| 72 |
| 7 | PLLuM 12B | 3/30 (10%) |
|
| 73 |
|
| 74 |
+
Pełna metodyka, kod, klucz odpowiedzi i analiza per-zadaniowa: [github.com/agentGreg/egzamin-8-klasisty-maly-llm](https://github.com/agentGreg/egzamin-8-klasisty-maly-llm)
|
| 75 |
|
| 76 |
## Atrybucja
|
| 77 |
|
|
|
|
| 99 |
|
| 100 |
---
|
| 101 |
|
| 102 |
+
*Wagi MLX przygotowane w ramach benchmarku [Egzamin ósmoklasisty z matematyki 2026 — benchmark małych LLM-ów](https://github.com/agentGreg/egzamin-8-klasisty-maly-llm) by [Prosit AS](https://prosit.no).*
|