chore(model gallery): add lb-reranker-0.5b-v1.0 (#4611)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-03-23 04:25:32 +00:00 · 2025-01-15 15:54:12 +01:00 · 2025-01-15 15:54:12 +01:00 · 6d20497d45
commit 6d20497d45
parent 482c6b8be4
1 changed files with 30 additions and 0 deletions
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@ -3171,6 +3171,36 @@
    - filename: Qwerus-7B-Q4_K_M.gguf
      sha256: 3676629e8092a59f523393e6eb5072727f5213a9e03b7b81141f05a33743e20c
      uri: huggingface://bartowski/Qwerus-7B-GGUF/Qwerus-7B-Q4_K_M.gguf
+- !!merge <<: *qwen25
+  name: "lb-reranker-0.5b-v1.0"
+  urls:
+    - https://huggingface.co/lightblue/lb-reranker-0.5B-v1.0
+    - https://huggingface.co/bartowski/lb-reranker-0.5B-v1.0-GGUF
+  description: |
+    The LB Reranker has been trained to determine the relatedness of a given query to a piece of text, therefore allowing it to be used as a ranker or reranker in various retrieval-based tasks.
+
+    This model is fine-tuned from a Qwen/Qwen2.5-0.5B-Instruct model checkpoint and was trained for roughly 5.5 hours using the 8 x L20 instance (ecs.gn8is-8x.32xlarge) on Alibaba Cloud.
+
+    The training data for this model can be found at lightblue/reranker_continuous_filt_max7_train and the code for generating this data as well as running the training of the model can be found on our Github repo.
+
+    Trained on data in over 95 languages, this model is applicable to a broad range of use cases.
+
+    This model has three main benefits over comparable rerankers.
+
+        It has shown slightly higher performance on evaluation benchmarks.
+        It has been trained on more languages than any previous model.
+        It is a simple Causal LM model trained to output a string between "1" and "7".
+
+    This last point means that this model can be used natively with many widely available inference packages, including vLLM and LMDeploy. This in turns allows our reranker to benefit from improvements to inference as and when these packages release them.
+
+    Update: We have also found that this model works pretty well as a code snippet reranker too (P@1 of 96%)! See our Colab for more details.
+  overrides:
+    parameters:
+      model: lb-reranker-0.5B-v1.0-Q4_K_M.gguf
+  files:
+    - filename: lb-reranker-0.5B-v1.0-Q4_K_M.gguf
+      sha256: 43568150de5136da15c996bbf4d1a78cc6580515c40f0ef9a8c90b0542228ab3
+      uri: huggingface://bartowski/lb-reranker-0.5B-v1.0-GGUF/lb-reranker-0.5B-v1.0-Q4_K_M.gguf
 - &smollm
  ## SmolLM
  url: "github:mudler/LocalAI/gallery/chatml.yaml@master"