Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- compiled/11808f3ab01b12ced35a.neff +3 -0
- compiled/82ba4474adc4b742f2c1.neff +3 -0
- config.json +39 -0
- generation_config.json +14 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
compiled/11808f3ab01b12ced35a.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/82ba4474adc4b742f2c1.neff filter=lfs diff=lfs merge=lfs -text
|
compiled/11808f3ab01b12ced35a.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a5c01209af0decaca91d663201ce894c717f703d2f325cb0298fbf9f7e06a2
|
3 |
+
size 16231424
|
compiled/82ba4474adc4b742f2c1.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:003280cdd29996f0191dde3a299823591d00a0b9466cef9338acd356fded8c6a
|
3 |
+
size 3953664
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"neuron": {
|
17 |
+
"auto_cast_type": "bf16",
|
18 |
+
"batch_size": 32,
|
19 |
+
"checkpoint_id": "Qwen/Qwen2.5-7B-Instruct",
|
20 |
+
"checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75",
|
21 |
+
"compiler_type": "neuronx-cc",
|
22 |
+
"compiler_version": "2.15.143.0+e39249ad",
|
23 |
+
"num_cores": 24,
|
24 |
+
"sequence_length": 4096,
|
25 |
+
"task": "text-generation"
|
26 |
+
},
|
27 |
+
"num_attention_heads": 28,
|
28 |
+
"num_hidden_layers": 28,
|
29 |
+
"num_key_value_heads": 4,
|
30 |
+
"rms_norm_eps": 1e-06,
|
31 |
+
"rope_theta": 1000000.0,
|
32 |
+
"sliding_window": null,
|
33 |
+
"tie_word_embeddings": false,
|
34 |
+
"torch_dtype": "bfloat16",
|
35 |
+
"transformers_version": "4.43.2",
|
36 |
+
"use_cache": true,
|
37 |
+
"use_sliding_window": false,
|
38 |
+
"vocab_size": 152064
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.43.2"
|
14 |
+
}
|