Upload 10 files
Browse files- config.json +43 -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.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NeverSleep/Lumimaid-v0.2-70B",
|
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 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 8192,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 28672,
|
15 |
+
"max_position_embeddings": 131072,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 64,
|
19 |
+
"num_hidden_layers": 80,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"quantization_config": {
|
23 |
+
"activation_scheme": "dynamic",
|
24 |
+
"ignored_layers": [
|
25 |
+
"lm_head"
|
26 |
+
],
|
27 |
+
"quant_method": "fp8"
|
28 |
+
},
|
29 |
+
"rms_norm_eps": 1e-05,
|
30 |
+
"rope_scaling": {
|
31 |
+
"factor": 8.0,
|
32 |
+
"high_freq_factor": 4.0,
|
33 |
+
"low_freq_factor": 1.0,
|
34 |
+
"original_max_position_embeddings": 8192,
|
35 |
+
"rope_type": "llama3"
|
36 |
+
},
|
37 |
+
"rope_theta": 500000.0,
|
38 |
+
"tie_word_embeddings": false,
|
39 |
+
"torch_dtype": "bfloat16",
|
40 |
+
"transformers_version": "4.45.2",
|
41 |
+
"use_cache": false,
|
42 |
+
"vocab_size": 128256
|
43 |
+
}
|
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": "4.45.2"
|
12 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ad80a0a9040a69b87a74dc64e7ce24d94f6661a022a8b108f7203b244cc7b20
|
3 |
+
size 4819359900
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30f5ebb5744d604a87dfc8e8688d6febbe623e4a4ed4d59daf3059bdbfa4c8a9
|
3 |
+
size 4983039376
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e45dc9cdcc7547e5124368bd15d1bee5f2e256ec076a6d57733754ac7903815
|
3 |
+
size 4899121052
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66cd6aa81045f6cf59bbd2b08d2787868705f469a89e69d97f7f21b34d489823
|
3 |
+
size 4899154060
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c2e4a3e15126edafba3d270c3b469ca4ac2852520c0a0999431f8edda3951a9
|
3 |
+
size 4899154060
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff45af591076353c5f54fef43440a432af702920029df003b425e093a70839a2
|
3 |
+
size 4983039464
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16055441b9a03e75048e4707599ad2130299b49f4158aecb66ba9f22f8dd410c
|
3 |
+
size 4899121068
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|