Instructions to use anocha-mcomp/lora_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anocha-mcomp/lora_model with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("anocha-mcomp/lora_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Update model card from Confluence: Qwen-SEA-LION-v4.5-27B Draft
Browse files- qwen-sea-lion-v45-27b_draft.md +15 -13
qwen-sea-lion-v45-27b_draft.md
CHANGED
|
@@ -1,20 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Card for Qwen-SEA-LION-v4.5-27B
|
| 2 |
|
| 3 |
Last update: 2026-05-19
|
| 4 |
|
| 5 |
**SEA-LION** is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
|
| 6 |
|
| 7 |
-
**Qwen-SEA-LION-v4.5-27B** built upon the Qwen3.6-27B dense architecture, a 27-billion parameter model featuring a hybrid Linear and Full Attention design. To ensure deep domain adaptation, the model underwent distillation from
|
| 8 |
|
| 9 |
Qwen-SEA-LION-v4.5-27B inherits the following features from Qwen3.6:
|
| 10 |
|
| 11 |
-
- **Context Window (262K):**
|
| 12 |
-
- **
|
| 13 |
-
- **Scalable RL:** Trained in million-agent environments for robust, real-world SEA adaptability.
|
| 14 |
-
- **Broad Linguistic Coverage:** Deeply specialized in SEA cultural nuances while supporting 201 languages globally.
|
| 15 |
-
- **Advanced Infrastructure:** Utilizes highly efficient multimodal training and asynchronous RL frameworks.
|
| 16 |
-
- **Agentic Coding:** High-precision handling of repository-level reasoning and frontend workflows.
|
| 17 |
- **Thinking Preservation:** Retains historical reasoning context to streamline iterative development and reduce compute overhead.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
|
@@ -22,7 +24,7 @@ Qwen-SEA-LION-v4.5-27B inherits the following features from Qwen3.6:
|
|
| 22 |
|
| 23 |
SEA-LION stands for Southeast Asian Languages In One Network.
|
| 24 |
|
| 25 |
-
We performed post-training in English and SEA languages on Qwen3.6-27B, a multimodal learning model using the Qwen3.6 architecture, to create Qwen-SEA-LION-v4.5.
|
| 26 |
|
| 27 |
For tokenization, the model employs the default tokenizer used in Qwen3.6.
|
| 28 |
|
|
@@ -557,12 +559,12 @@ For details on Qwen-SEA-LION-v4.5-27B performance, please refer to the [SEA-LION
|
|
| 557 |
| H200 | 34.4 GB | 51.1 GiB | 0.0512 | 69.9005 |
|
| 558 |
| H100 | 34.4 GB | 51.1 GiB | | |
|
| 559 |
|
| 560 |
-
> Additional Remarks:
|
| 561 |
>
|
| 562 |
-
> - TTFT and Tokens per Second: measured with vllm on localhost and concurrency = 1.
|
| 563 |
-
> - Offload all layers to GPU, Context Length 8192
|
| 564 |
-
> - Reported results are the median (p50) values, calculated across 10 requests.
|
| 565 |
-
> - Input size 4K, output 1K
|
| 566 |
>
|
| 567 |
|
| 568 |
## Technical Specifications
|
|
|
|
| 1 |
+
# Qwen-SEA-LION-v4.5-27B Draft
|
| 2 |
+
|
| 3 |
+
``
|
| 4 |
+
|
| 5 |
# Model Card for Qwen-SEA-LION-v4.5-27B
|
| 6 |
|
| 7 |
Last update: 2026-05-19
|
| 8 |
|
| 9 |
**SEA-LION** is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
|
| 10 |
|
| 11 |
+
**Qwen-SEA-LION-v4.5-27B** built upon the Qwen3.6-27B dense architecture, a 27-billion parameter model featuring a hybrid Linear and Full Attention design. To ensure deep domain adaptation, the model underwent distillation from Qwen3.5-397B-A17B on an updated aisingapore/SEA-Instruct-2602, instilling multilingual and multicultural fluency across English and key SEA languages including: Burmese, Indonesian, Filipino, Malay, Tamil, Thai, and Vietnamese.
|
| 12 |
|
| 13 |
Qwen-SEA-LION-v4.5-27B inherits the following features from Qwen3.6:
|
| 14 |
|
| 15 |
+
- **Context Window (262K):** Large context window to enable strong reasoning capabilities.
|
| 16 |
+
- **Reasoning** – Highly capable reasoning model, with configurable thinking modes.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
- **Thinking Preservation:** Retains historical reasoning context to streamline iterative development and reduce compute overhead.
|
| 18 |
+
- **Agentic Coding:** High-precision handling of repository-level reasoning and frontend workflows.
|
| 19 |
+
- **Unified Vision-Language:** Early fusion training delivers good performance across multimodal reasoning, coding, and visual tasks.
|
| 20 |
|
| 21 |
## Model Details
|
| 22 |
|
|
|
|
| 24 |
|
| 25 |
SEA-LION stands for Southeast Asian Languages In One Network.
|
| 26 |
|
| 27 |
+
We performed post-training in English and SEA languages on Qwen3.6-27B, a multimodal learning model using the Qwen3.6 architecture, to create Qwen-SEA-LION-v4.5-27B.
|
| 28 |
|
| 29 |
For tokenization, the model employs the default tokenizer used in Qwen3.6.
|
| 30 |
|
|
|
|
| 559 |
| H200 | 34.4 GB | 51.1 GiB | 0.0512 | 69.9005 |
|
| 560 |
| H100 | 34.4 GB | 51.1 GiB | | |
|
| 561 |
|
| 562 |
+
> *Additional Remarks:*
|
| 563 |
>
|
| 564 |
+
> - *TTFT and Tokens per Second: measured with vllm on localhost and concurrency = 1.*
|
| 565 |
+
> - *Offload all layers to GPU, Context Length 8192*
|
| 566 |
+
> - *Reported results are the median (p50) values, calculated across 10 requests.*
|
| 567 |
+
> - *Input size 4K, output 1K*
|
| 568 |
>
|
| 569 |
|
| 570 |
## Technical Specifications
|