Improve model card: Add pipeline tag, library name, paper & code links
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,13 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
datasets:
|
| 4 |
- codefuse-ai/F2LLM
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
-
|
| 8 |
-
|
|
|
|
| 9 |
---
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
F2LLMs (Foundation to Feature Large Language Models) are foundation models directly finetuned on 6 million high-quality query-document pairs (available in [codefuse-ai/F2LLM](https://huggingface.co/datasets/codefuse-ai/F2LLM)) covering a diverse range of retrieval, classification, and clustering data, curated solely from open-source datasets without any synthetic data. These models are trained with homogeneous macro batches in a single stage, without sophisticated multi-stage pipelines.
|
| 12 |
|
| 13 |
## Usage
|
|
@@ -84,4 +91,4 @@ If you use the F2LLM models, data, or code, please cite the following technical
|
|
| 84 |
eprinttype = {arXiv},
|
| 85 |
eprint = {2510.02294}
|
| 86 |
}
|
| 87 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Qwen/Qwen3-1.7B
|
| 4 |
datasets:
|
| 5 |
- codefuse-ai/F2LLM
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
pipeline_tag: feature-extraction
|
| 10 |
+
library_name: transformers
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
|
| 14 |
+
|
| 15 |
+
This model is presented in the paper [F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data](https://huggingface.co/papers/2510.02294).
|
| 16 |
+
The code for this model is available on [GitHub](https://github.com/codefuse-ai/CodeFuse-Embeddings/tree/main/F2LLM).
|
| 17 |
+
|
| 18 |
F2LLMs (Foundation to Feature Large Language Models) are foundation models directly finetuned on 6 million high-quality query-document pairs (available in [codefuse-ai/F2LLM](https://huggingface.co/datasets/codefuse-ai/F2LLM)) covering a diverse range of retrieval, classification, and clustering data, curated solely from open-source datasets without any synthetic data. These models are trained with homogeneous macro batches in a single stage, without sophisticated multi-stage pipelines.
|
| 19 |
|
| 20 |
## Usage
|
|
|
|
| 91 |
eprinttype = {arXiv},
|
| 92 |
eprint = {2510.02294}
|
| 93 |
}
|
| 94 |
+
```
|