Upload 13 files
Browse files- config.json +42 -0
- generation_config.json +12 -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-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Sao10K/L3.1-70B-Euryale-v2.2",
|
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": 131072,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 64,
|
18 |
+
"num_hidden_layers": 80,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"quantization_config": {
|
22 |
+
"activation_scheme": "dynamic",
|
23 |
+
"ignored_layers": [
|
24 |
+
"lm_head"
|
25 |
+
],
|
26 |
+
"quant_method": "fp8"
|
27 |
+
},
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": {
|
30 |
+
"factor": 8.0,
|
31 |
+
"high_freq_factor": 4.0,
|
32 |
+
"low_freq_factor": 1.0,
|
33 |
+
"original_max_position_embeddings": 8192,
|
34 |
+
"rope_type": "llama3"
|
35 |
+
},
|
36 |
+
"rope_theta": 500000.0,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "float16",
|
39 |
+
"transformers_version": "4.44.2",
|
40 |
+
"use_cache": false,
|
41 |
+
"vocab_size": 128256
|
42 |
+
}
|
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 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.44.2"
|
12 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9906c78c6b062f9c135103b7e769449f9bb6b367f5edff9d01d52a920672f6be
|
3 |
+
size 4819359892
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aa8a6d8950cfeb6d1a2be5c0666b0fc17864b2e9f29431cbe0d6081e48b7afc
|
3 |
+
size 4983039360
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76c633ed579c4a864ea4579f780f1154047a7289d12fd83776cea864755ca34e
|
3 |
+
size 4899121044
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad9d986b44b337b6d6dfc78a5ca984939cc75beda43f2614981d03bcef9fbb4b
|
3 |
+
size 4899154052
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f93b340603227bb806db9213bf3b807453ef2a73c28154bcb4d85383af698b09
|
3 |
+
size 4899154052
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae554e964e15e489e9f3a8fa12929aab0949c50e65d298bd17d1e7c66bb6c83
|
3 |
+
size 4983039448
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53f2c28f6a8540da813ece1d292ea6777c6a8450a02862535288bf6a318fc861
|
3 |
+
size 4899121060
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb3f5fe3dc8b6ca83dc8fdb7da63e1004764ba88dd80b2b9bc2c71b3fad93f9a
|
3 |
+
size 4899154052
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c14355c7865e9a6e86f3cd0f755d44cf249f851ccd59b6b9aaed3e95dae80af2
|
3 |
+
size 4899154052
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6ad9e2ec77b5708c8cf7d7806a3f01bec06658c236bd362f95a9802fe28dfc1
|
3 |
+
size 4983039448
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|