Trained with Unsloth
Browse files- README.md +4 -1
- config.json +5 -6
- generation_config.json +2 -0
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
README.md
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
tags:
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- unsloth
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
---
|
8 |
|
9 |
# Model Card for Model ID
|
config.json
CHANGED
@@ -1,16 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
10 |
-
128001,
|
11 |
-
128008,
|
12 |
-
128009
|
13 |
-
],
|
14 |
"head_dim": 128,
|
15 |
"hidden_act": "silu",
|
16 |
"hidden_size": 4096,
|
@@ -22,6 +18,7 @@
|
|
22 |
"num_attention_heads": 32,
|
23 |
"num_hidden_layers": 32,
|
24 |
"num_key_value_heads": 8,
|
|
|
25 |
"pretraining_tp": 1,
|
26 |
"rms_norm_eps": 1e-05,
|
27 |
"rope_scaling": {
|
@@ -35,6 +32,8 @@
|
|
35 |
"tie_word_embeddings": false,
|
36 |
"torch_dtype": "bfloat16",
|
37 |
"transformers_version": "4.49.0",
|
|
|
|
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 128256
|
40 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
|
|
|
|
|
|
|
|
10 |
"head_dim": 128,
|
11 |
"hidden_act": "silu",
|
12 |
"hidden_size": 4096,
|
|
|
18 |
"num_attention_heads": 32,
|
19 |
"num_hidden_layers": 32,
|
20 |
"num_key_value_heads": 8,
|
21 |
+
"pad_token_id": 128004,
|
22 |
"pretraining_tp": 1,
|
23 |
"rms_norm_eps": 1e-05,
|
24 |
"rope_scaling": {
|
|
|
32 |
"tie_word_embeddings": false,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
"transformers_version": "4.49.0",
|
35 |
+
"unsloth_fixed": true,
|
36 |
+
"unsloth_version": "2025.3.9",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 128256
|
39 |
}
|
generation_config.json
CHANGED
@@ -6,6 +6,8 @@
|
|
6 |
128008,
|
7 |
128009
|
8 |
],
|
|
|
|
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
"transformers_version": "4.49.0"
|
|
|
6 |
128008,
|
7 |
128009
|
8 |
],
|
9 |
+
"max_length": 131072,
|
10 |
+
"pad_token_id": 128004,
|
11 |
"temperature": 0.6,
|
12 |
"top_p": 0.9,
|
13 |
"transformers_version": "4.49.0"
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba6b6f07c6bc136cb80f29f7fca7ccbb4b4afa1e0fd43d5a8d8a3275612526a0
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7210de1331d1a49376804e292af703f52ed42d9408311bbce5332950c22b87d8
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afcf9d5d27c4a4f270a37745565ca1945e4a7e3e38fdb831571df431c55dc675
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5f1829d807b99221114c83a0012a5f818f7db79894708658b5b8210a5bba659
|
3 |
size 1168138808
|