Skip to content

Commit 838a005

Browse files
committed
chore(model gallery): add menlo_rezero-v0.1-llama-3.2-3b-it-grpo-250404
Signed-off-by: Ettore Di Giacinto <[email protected]>
1 parent a2ef4b1 commit 838a005

File tree

1 file changed

+14
-0
lines changed

1 file changed

+14
-0
lines changed

gallery/index.yaml

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2688,6 +2688,20 @@
26882688
- filename: deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf
26892689
sha256: 726a0ef5f818b8d238f2844f3204848bea66fb9c172b8ae0f6dc51b7bc081dd5
26902690
uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf
2691+
- !!merge <<: *llama32
2692+
name: "menlo_rezero-v0.1-llama-3.2-3b-it-grpo-250404"
2693+
urls:
2694+
- https://huggingface.co/Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
2695+
- https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF
2696+
description: |
2697+
ReZero trains a small language model to develop effective search behaviors instead of memorizing static data. It interacts with multiple synthetic search engines, each with unique retrieval mechanisms, to refine queries and persist in searching until it finds exact answers. The project focuses on reinforcement learning, preventing overfitting, and optimizing for efficiency in real-world search applications.
2698+
overrides:
2699+
parameters:
2700+
model: Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf
2701+
files:
2702+
- filename: Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf
2703+
sha256: b9f01bead9e163db9351af036d8d63ef479d7d48a1bb44934ead732a180f371c
2704+
uri: huggingface://bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf
26912705
- &qwen25
26922706
name: "qwen2.5-14b-instruct" ## Qwen2.5
26932707
icon: https://avatars.githubusercontent.com/u/141221163

0 commit comments

Comments
 (0)