Upload folder using huggingface_hub
Browse files- README.md +25 -6
- config.json +43 -1
- generation_config.json +1 -1
- model.safetensors.index.json +1 -0
README.md
CHANGED
|
@@ -6,6 +6,23 @@ base_model:
|
|
| 6 |
license: apache-2.0
|
| 7 |
library_name: transformers
|
| 8 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
# Qwen3-14B-Base
|
| 10 |
|
| 11 |
## Qwen3 Highlights
|
|
@@ -49,11 +66,13 @@ Detailed evaluation results are reported in this [📑 blog](https://qwenlm.gith
|
|
| 49 |
If you find our work helpful, feel free to give us a cite.
|
| 50 |
|
| 51 |
```
|
| 52 |
-
@misc{
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
| 58 |
}
|
| 59 |
```
|
|
|
|
| 6 |
license: apache-2.0
|
| 7 |
library_name: transformers
|
| 8 |
---
|
| 9 |
+
<div>
|
| 10 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 11 |
+
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
| 12 |
+
</p>
|
| 13 |
+
<div style="display: flex; gap: 5px; align-items: center; ">
|
| 14 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 15 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 16 |
+
</a>
|
| 17 |
+
<a href="https://discord.gg/unsloth">
|
| 18 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 19 |
+
</a>
|
| 20 |
+
<a href="https://docs.unsloth.ai/">
|
| 21 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 22 |
+
</a>
|
| 23 |
+
</div>
|
| 24 |
+
</div>
|
| 25 |
+
|
| 26 |
# Qwen3-14B-Base
|
| 27 |
|
| 28 |
## Qwen3 Highlights
|
|
|
|
| 66 |
If you find our work helpful, feel free to give us a cite.
|
| 67 |
|
| 68 |
```
|
| 69 |
+
@misc{qwen3technicalreport,
|
| 70 |
+
title={Qwen3 Technical Report},
|
| 71 |
+
author={Qwen Team},
|
| 72 |
+
year={2025},
|
| 73 |
+
eprint={2505.09388},
|
| 74 |
+
archivePrefix={arXiv},
|
| 75 |
+
primaryClass={cs.CL},
|
| 76 |
+
url={https://arxiv.org/abs/2505.09388},
|
| 77 |
}
|
| 78 |
```
|
config.json
CHANGED
|
@@ -10,6 +10,48 @@
|
|
| 10 |
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 17408,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
"max_window_layers": 40,
|
| 15 |
"model_type": "qwen3",
|
|
@@ -23,7 +65,7 @@
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"unsloth_fixed": true,
|
| 28 |
"use_cache": true,
|
| 29 |
"use_sliding_window": false,
|
|
|
|
| 10 |
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 17408,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention"
|
| 54 |
+
],
|
| 55 |
"max_position_embeddings": 32768,
|
| 56 |
"max_window_layers": 40,
|
| 57 |
"model_type": "qwen3",
|
|
|
|
| 65 |
"sliding_window": null,
|
| 66 |
"tie_word_embeddings": false,
|
| 67 |
"torch_dtype": "bfloat16",
|
| 68 |
+
"transformers_version": "4.53.2",
|
| 69 |
"unsloth_fixed": true,
|
| 70 |
"use_cache": true,
|
| 71 |
"use_sliding_window": false,
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"max_length": 32768,
|
| 5 |
"max_new_tokens": 2048,
|
| 6 |
"pad_token_id": 151654,
|
| 7 |
-
"transformers_version": "4.
|
| 8 |
}
|
|
|
|
| 4 |
"max_length": 32768,
|
| 5 |
"max_new_tokens": 2048,
|
| 6 |
"pad_token_id": 151654,
|
| 7 |
+
"transformers_version": "4.53.2"
|
| 8 |
}
|
model.safetensors.index.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
|
|
|
| 3 |
"total_size": 29536614400
|
| 4 |
},
|
| 5 |
"weight_map": {
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 14768307200,
|
| 4 |
"total_size": 29536614400
|
| 5 |
},
|
| 6 |
"weight_map": {
|