Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +4 -0
- config.json +32 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,3 +1,7 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- unsloth
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
---
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Sakalti/Saba1-1.8B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1536,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8960,
|
13 |
+
"max_position_embeddings": 131072,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"pad_token_id": 151654,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"sliding_window": null,
|
24 |
+
"tie_word_embeddings": true,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.46.3",
|
27 |
+
"unsloth_version": "2024.12.4",
|
28 |
+
"use_cache": true,
|
29 |
+
"use_mrope": false,
|
30 |
+
"use_sliding_window": false,
|
31 |
+
"vocab_size": 151936
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"eos_token_id": 151643,
|
5 |
+
"max_length": 131072,
|
6 |
+
"pad_token_id": 151654,
|
7 |
+
"transformers_version": "4.46.3"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a3a644270cfa3c503ebb6773fd3456c05e7e1481aa21dfb3a064230e491ffec
|
3 |
+
size 3087466808
|