(Trained with Unsloth)
Browse files- config.json +5 -5
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +0 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "unsloth/mistral-7b-
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -16,15 +16,15 @@
|
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
-
"pad_token_id":
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
22 |
-
"rope_theta":
|
23 |
-
"sliding_window":
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
"transformers_version": "4.42.4",
|
27 |
"unsloth_version": "2024.7",
|
28 |
"use_cache": true,
|
29 |
-
"vocab_size":
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/mistral-7b-bnb-4bit",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 2,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"sliding_window": 4096,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
"transformers_version": "4.42.4",
|
27 |
"unsloth_version": "2024.7",
|
28 |
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5707c2b0b6d5f391aaa82e49cf705d704c4186ddef769561353182a31e407a3a
|
3 |
+
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:669d3c5dc665f3dd3652c8d2eb4e66f1aaba0e310cfa5c1de2816d37983fca5a
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7fb9c6bf3e804b3129ab527a3d84a31cdc04ac0c1aa7358522d2edd096e417d
|
3 |
+
size 4540516256
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
special_tokens_map.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|