Trained with Unsloth
Browse files- config.json +3 -8
- generation_config.json +6 -1
- 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
config.json
CHANGED
@@ -3,7 +3,6 @@
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
6 |
-
"bos_token_id": 151643,
|
7 |
"eos_token_id": 151645,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 3584,
|
@@ -15,14 +14,10 @@
|
|
15 |
"num_attention_heads": 28,
|
16 |
"num_hidden_layers": 28,
|
17 |
"num_key_value_heads": 4,
|
18 |
-
"pad_token_id":
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
-
"rope_scaling":
|
21 |
-
|
22 |
-
"rope_type": "linear",
|
23 |
-
"type": "linear"
|
24 |
-
},
|
25 |
-
"rope_theta": 10000.0,
|
26 |
"sliding_window": null,
|
27 |
"tie_word_embeddings": false,
|
28 |
"torch_dtype": "bfloat16",
|
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
|
|
6 |
"eos_token_id": 151645,
|
7 |
"hidden_act": "silu",
|
8 |
"hidden_size": 3584,
|
|
|
14 |
"num_attention_heads": 28,
|
15 |
"num_hidden_layers": 28,
|
16 |
"num_key_value_heads": 4,
|
17 |
+
"pad_token_id": 151654,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 1000000.0,
|
|
|
|
|
|
|
|
|
21 |
"sliding_window": null,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
generation_config.json
CHANGED
@@ -1,10 +1,15 @@
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
|
|
3 |
"eos_token_id": [
|
4 |
151645,
|
5 |
151643
|
6 |
],
|
7 |
"max_length": 32768,
|
8 |
-
"pad_token_id":
|
|
|
|
|
|
|
|
|
9 |
"transformers_version": "4.51.1"
|
10 |
}
|
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
151645,
|
6 |
151643
|
7 |
],
|
8 |
"max_length": 32768,
|
9 |
+
"pad_token_id": 151654,
|
10 |
+
"repetition_penalty": 1.05,
|
11 |
+
"temperature": 0.7,
|
12 |
+
"top_k": 20,
|
13 |
+
"top_p": 0.8,
|
14 |
"transformers_version": "4.51.1"
|
15 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ff3b270cb6b8ce8a059a43678cebaefb7aa2a3b587aadc5a4e2f6c1e4d13a28
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:854698ca4d7581b9fd40f5da9176b010422194ec26cab3abd907ff21e477d1ca
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6295baeb13806b95509f86175dd3a298bf39630071a4dc2b2d31441c9230b011
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
|
3 |
size 1089994880
|