Upload LlamaForCausalLM
Browse files- config.json +69 -0
- generation_config.json +12 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-70B-Instruct/snapshots/1d54af340dc8906a2d21146191a9c184c35e47bd",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"compression_config": {
|
10 |
+
"config_groups": {
|
11 |
+
"group_0": {
|
12 |
+
"input_activations": null,
|
13 |
+
"output_activations": null,
|
14 |
+
"targets": [
|
15 |
+
"Linear"
|
16 |
+
],
|
17 |
+
"weights": {
|
18 |
+
"block_structure": null,
|
19 |
+
"dynamic": false,
|
20 |
+
"group_size": 128,
|
21 |
+
"num_bits": 4,
|
22 |
+
"observer": "minmax",
|
23 |
+
"observer_kwargs": {},
|
24 |
+
"strategy": "group",
|
25 |
+
"symmetric": true,
|
26 |
+
"type": "int"
|
27 |
+
}
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"format": "pack-quantized",
|
31 |
+
"global_compression_ratio": 1.9030208016028207,
|
32 |
+
"ignore": [
|
33 |
+
"lm_head"
|
34 |
+
],
|
35 |
+
"kv_cache_scheme": null,
|
36 |
+
"quant_method": "compressed-tensors",
|
37 |
+
"quantization_status": "frozen"
|
38 |
+
},
|
39 |
+
"eos_token_id": [
|
40 |
+
128001,
|
41 |
+
128008,
|
42 |
+
128009
|
43 |
+
],
|
44 |
+
"hidden_act": "silu",
|
45 |
+
"hidden_size": 8192,
|
46 |
+
"initializer_range": 0.02,
|
47 |
+
"intermediate_size": 28672,
|
48 |
+
"max_position_embeddings": 131072,
|
49 |
+
"mlp_bias": false,
|
50 |
+
"model_type": "llama",
|
51 |
+
"num_attention_heads": 64,
|
52 |
+
"num_hidden_layers": 80,
|
53 |
+
"num_key_value_heads": 8,
|
54 |
+
"pretraining_tp": 1,
|
55 |
+
"rms_norm_eps": 1e-05,
|
56 |
+
"rope_scaling": {
|
57 |
+
"factor": 8.0,
|
58 |
+
"high_freq_factor": 4.0,
|
59 |
+
"low_freq_factor": 1.0,
|
60 |
+
"original_max_position_embeddings": 8192,
|
61 |
+
"rope_type": "llama3"
|
62 |
+
},
|
63 |
+
"rope_theta": 500000.0,
|
64 |
+
"tie_word_embeddings": false,
|
65 |
+
"torch_dtype": "bfloat16",
|
66 |
+
"transformers_version": "4.44.0",
|
67 |
+
"use_cache": true,
|
68 |
+
"vocab_size": 128256
|
69 |
+
}
|
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": "4.44.0"
|
12 |
+
}
|
model-00001-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d6fcf810820cdc9c9397edc4bb32a7c5f0e98786b7a4b1164da2c7adbb2102
|
3 |
+
size 4947658664
|
model-00002-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a159cd8c9ee808a05fcd9c82c983d733ec6203f69a33c1f992d9d3185a794b2f
|
3 |
+
size 4974573352
|
model-00003-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4065845dae154b51e7bdd2bef23f33bba5c0b2d993b6e2432362df3d1f452f0b
|
3 |
+
size 4974606440
|
model-00004-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef9ec6b80c4a20a9e8453e1534b82b81ba364765653e0be3989d512a35ff1f7d
|
3 |
+
size 4931320776
|
model-00005-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:729acec917af0e3d0879c984083588374c53b1d90dcd98a91f39c486c9e59197
|
3 |
+
size 4974573440
|
model-00006-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d905973d70cfd5fe1a5739b8c9ffee4a8a2c8a26c4f7cb1e4e95557e893f672
|
3 |
+
size 4974573440
|
model-00007-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce8d04f466c284a31fa9ca3d663e8b5110e0c2553edf7eca2e5fb5c31974b53
|
3 |
+
size 4974606440
|
model-00008-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d9e1da03d6aec2dff2bafa33e46889f46906d67a7afdeded7264e736ea68a11
|
3 |
+
size 4748705944
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|