mlx-examples/llms/mlx_lm/tuner
L 0164d2058b
feat: DeepSeek MoE v1 (#942)
* feat: deepseek v1

DeepSeek is still releasing models on the DeepSeek V1 architecture.

```sh
mlx_lm.convert --hf-path deepseek-ai/DeepSeek-Prover-V1.5-RL --mlx-path DeepSeek-Prover-V1.5-RL-8bit --q-bits 8 -q
mlx_lm.generate --model DeepSeek-Prover-V1.5-RL-8bit --ignore-chat-template --max-tokens 512 --prompt 'import Mathlib
import Aesop

set_option maxHeartbeats 0

open BigOperators Real Nat Topology Rat

/-- The second and fourth terms of a geometric sequence are $2$ and $6$. Which of the following is a possible first term?
Show that it is $\frac{2\sqrt{3}}{3}$.-/
theorem amc12b_2003_p6 (a r : ℝ) (u : ℕ → ℝ) (h₀ : ∀ k, u k = a * r ^ k) (h₁ : u 1 = 2)
  (h₂ : u 3 = 6) : u 0 = 2 / Real.sqrt 3 ∨ u 0 = -(2 / Real.sqrt 3) := by'
```

* nits

* nits

* nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-08-17 07:18:09 -07:00
..
__init__.py LoRA: Extract small function (#614) 2024-06-02 06:38:42 -07:00
datasets.py Configuration-based use of HF hub-hosted datasets for training (#701) 2024-06-26 10:20:50 -07:00
dora.py Allow the entire model to be targed for LoRA and DoRA fine tuning: LoRA and DoRA embeddings with small DoRALinear bug fix (#914) 2024-08-16 07:38:36 -07:00
lora.py Allow the entire model to be targed for LoRA and DoRA fine tuning: LoRA and DoRA embeddings with small DoRALinear bug fix (#914) 2024-08-16 07:38:36 -07:00
trainer.py Add eos token to lora fine-tunes (#818) 2024-06-12 07:44:21 -07:00
utils.py feat: DeepSeek MoE v1 (#942) 2024-08-17 07:18:09 -07:00