Commit
•
07eeb78
1
Parent(s):
7231687
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- compiled/8df95e5492ce7b507bc9.neff +3 -0
- compiled/b6b7121eb33bdf2b9d5d.neff +3 -0
- config.json +39 -0
- generation_config.json +12 -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/8df95e5492ce7b507bc9.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/b6b7121eb33bdf2b9d5d.neff filter=lfs diff=lfs merge=lfs -text
|
compiled/8df95e5492ce7b507bc9.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c2b9162af9d2ee44fc2f3a6985a18600a4a452b38bc49ca87ec5cd23a85cc0a
|
3 |
+
size 15197184
|
compiled/b6b7121eb33bdf2b9d5d.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f058cca23b88b801ccfa76b924f080a0ed6dc8fd8e656d6641cdd93070f9940
|
3 |
+
size 9718784
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-70B-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 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "llama",
|
16 |
+
"neuron": {
|
17 |
+
"auto_cast_type": "bf16",
|
18 |
+
"batch_size": 4,
|
19 |
+
"checkpoint_id": "meta-llama/Meta-Llama-3-70B-Instruct",
|
20 |
+
"checkpoint_revision": "359ec69a0f92259a3cd2da3bb01d31e16c260cfc",
|
21 |
+
"compiler_type": "neuronx-cc",
|
22 |
+
"compiler_version": "2.13.66.0+6dfecc895",
|
23 |
+
"num_cores": 24,
|
24 |
+
"sequence_length": 4096,
|
25 |
+
"task": "text-generation"
|
26 |
+
},
|
27 |
+
"num_attention_heads": 64,
|
28 |
+
"num_hidden_layers": 80,
|
29 |
+
"num_key_value_heads": 8,
|
30 |
+
"pretraining_tp": 1,
|
31 |
+
"rms_norm_eps": 1e-05,
|
32 |
+
"rope_scaling": null,
|
33 |
+
"rope_theta": 500000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.36.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 128256
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"max_length": 4096,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.36.2"
|
12 |
+
}
|