GRPO, Reinforcement Learning by danielhanchen · Pull Request #39 · unslothai/unsloth-zoo

danielhanchen · 2025-02-06T10:34:11Z

No description provided.

danielhanchen added 30 commits December 26, 2024 17:07

Update saving_utils.py

d79fa9e

Update compiler_replacements.py

f1b4dc5

Update compiler.py

cca00d0

Update compiler.py

a4785df

Update compiler.py

3bcdf3b

Update compiler.py

ca0a012

Update compiler.py

3bf6192

Update compiler.py

6bd8a5c

Compiler replacements

ded3c92

Update compiler.py

69bd9d8

Update compiler.py

f8c9219

Update compiler.py

1be44b2

Update compiler.py

b48e46c

Update compiler.py

791320c

Update compiler.py

08bf032

Update compiler.py

1125136

Update compiler.py

9dab19e

Update compiler.py

235662b

Update compiler.py

a8f0b3f

Update compiler.py

373ca78

Update compiler.py

f9f3e47

Update compiler.py

24e2311

Update compiler.py

52f8d48

Update compiler.py

4f91565

Update compiler.py

3355783

Update compiler.py

5827895

Update compiler.py

bf3ba11

Update compiler.py

4aa4215

Update compiler.py

be3672c

Update compiler.py

2ad2932

danielhanchen added 29 commits February 5, 2025 01:22

Update vllm_utils.py

f8dc60a

Update vllm_utils.py

ba5f53c

Update vllm_utils.py

fa7a266

rotary

2212c9e

Update vllm_utils.py

aeb1d9a

Update vllm_utils.py

e690437

Update vllm_utils.py

6410735

Update vllm_utils.py

09863a0

Update vllm_utils.py

aa521e5

Update vllm_utils.py

6df288a

Update vllm_utils.py

b97f298

Update vllm_utils.py

5774e11

Update vllm_utils.py

bb9c3f8

Update vllm_utils.py

2897ca2

Update vllm_utils.py

9a985d3

Update vllm_utils.py

d49668a

load lora from tensors

62cd59a

0.7.1 lora request

6a56b14

Update vllm_lora_request.py

cc75536

Update vllm_lora_request.py

86567e8

Update vllm_utils.py

2b56402

Update vllm_utils.py

b4460dc

Update vllm_utils.py

230524d

Update vllm_utils.py

23e7cde

Update vllm_utils.py

2b6481d

Update vllm_utils.py

780268f

Update vllm_utils.py

5f1ac5a

Update vllm_utils.py

b624c84

Update compiler.py

0520eca

danielhanchen merged commit 83f5318 into main Feb 6, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

GRPO, Reinforcement Learning#39

GRPO, Reinforcement Learning#39
danielhanchen merged 199 commits into
mainfrom
nightly

danielhanchen commented Feb 6, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

danielhanchen commented Feb 6, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants