Upload 8 files
Browse files- config.json +44 -0
- generation_config.json +9 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
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": 8192,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 28672,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 64,
|
23 |
+
"num_hidden_layers": 80,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pretraining_tp": 1,
|
26 |
+
"quantization_config": {
|
27 |
+
"activation_scheme": "dynamic",
|
28 |
+
"quant_method": "fp8"
|
29 |
+
},
|
30 |
+
"rms_norm_eps": 1e-05,
|
31 |
+
"rope_scaling": {
|
32 |
+
"factor": 8.0,
|
33 |
+
"high_freq_factor": 4.0,
|
34 |
+
"low_freq_factor": 1.0,
|
35 |
+
"original_max_position_embeddings": 8192,
|
36 |
+
"rope_type": "llama3"
|
37 |
+
},
|
38 |
+
"rope_theta": 500000.0,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"torch_dtype": "bfloat16",
|
41 |
+
"transformers_version": "4.45.2",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 128256
|
44 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"eos_token_id": [
|
4 |
+
128001,
|
5 |
+
128008,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"transformers_version": "4.45.2"
|
9 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623b1c6c72bdf0498a3e6a3f158842d9b039fc673aad59ea5094c0b3e1b27d5f
|
3 |
+
size 4819359900
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f75baddcdab10467d07946e043f1c0680309c8037c7bd91406a95f3ea859090
|
3 |
+
size 4983039376
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d609cf912c7f5f0fb15be05aacdd3a40182f9c0282d10e10e3d7892febe68b0
|
3 |
+
size 4899121052
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a85a2ec85dad9ffaddb057273257eb8fb9e157e7d0a4b08cbad78f14a68f95d
|
3 |
+
size 4899154060
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:323c50ea1764ae4a5f1e642935815dc7fd39750c5b19bb39db3a8997a468a687
|
3 |
+
size 4899154060
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|