fe80b163c39157ee7ee89a3aa632c35c8fca059444719bff797b26fb98bb6320
Browse files- .gitattributes +10 -0
- checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +3 -0
- compiled/42892ca1835c7f1ee360.neff +3 -0
- compiled/5f563a8109c06154fd1a.neff +3 -0
- compiled/81e045aa41db6708aa20.neff +3 -0
- compiled/9e156236317bf9a3f88c.neff +3 -0
- compiled/a5a606ee7f9b51e4eb22.neff +3 -0
- compiled/ba2c6f82564581eac7de.neff +3 -0
- compiled/bc1b3efbe17382b052dc.neff +3 -0
- compiled/c13580424e448f3adb62.neff +3 -0
- compiled/cd7da042b94df6a02f61.neff +3 -0
- compiled/d0dad260213be0bab13e.neff +3 -0
- config.json +37 -0
- generation_config.json +6 -0
.gitattributes
CHANGED
@@ -33,3 +33,13 @@ 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/42892ca1835c7f1ee360.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/5f563a8109c06154fd1a.neff filter=lfs diff=lfs merge=lfs -text
|
38 |
+
compiled/81e045aa41db6708aa20.neff filter=lfs diff=lfs merge=lfs -text
|
39 |
+
compiled/9e156236317bf9a3f88c.neff filter=lfs diff=lfs merge=lfs -text
|
40 |
+
compiled/a5a606ee7f9b51e4eb22.neff filter=lfs diff=lfs merge=lfs -text
|
41 |
+
compiled/ba2c6f82564581eac7de.neff filter=lfs diff=lfs merge=lfs -text
|
42 |
+
compiled/bc1b3efbe17382b052dc.neff filter=lfs diff=lfs merge=lfs -text
|
43 |
+
compiled/c13580424e448f3adb62.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
+
compiled/cd7da042b94df6a02f61.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
+
compiled/d0dad260213be0bab13e.neff filter=lfs diff=lfs merge=lfs -text
|
checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44ddcf0fdc37c330e1e4b95f04ef2438e1280d7c27b050fb1a27fa3b1fdd65e9
|
3 |
+
size 234881907
|
checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f14b99d819888161a9c1ff3f501ae31baa362f769fc6d99f2c07ee0ea7a2b86
|
3 |
+
size 234881913
|
checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4787f2932a6f6e1b19067a860815a6dd488b45f411035cc3084a7a0df8896d82
|
3 |
+
size 17279
|
checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1129e2dedc5186a59a3ecb2582634b4e20dfffcbd24ed09444c75d2dcdd0135c
|
3 |
+
size 17306
|
compiled/42892ca1835c7f1ee360.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2360b5a2fbcc8f95842dd05d82d0a33e314c4255b16a1bb4e3ded98aa1ebd619
|
3 |
+
size 26829824
|
compiled/5f563a8109c06154fd1a.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955ae6b6a812e0f92a9ef0f773f76f459b00df2cd20dd83d76c18cf28610710c
|
3 |
+
size 11367424
|
compiled/81e045aa41db6708aa20.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ac6027ce5c9b520f2bb0ab380a6cc350195f33be0c96d6d006ad6d3ba22b27
|
3 |
+
size 7947264
|
compiled/9e156236317bf9a3f88c.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f89c094db7ed55c0db17abf5ee08bdad14b0c02f67fa1c30d6198a46edc9620
|
3 |
+
size 7988224
|
compiled/a5a606ee7f9b51e4eb22.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08fec642d1ecac1f81dfc60018abec3b3d3c6135fdb71e45c7d4ec43303b5390
|
3 |
+
size 9042944
|
compiled/ba2c6f82564581eac7de.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42519f9424c5f94aaf9b006d42f3c02925a44db85140b240bc0dab5b519100ba
|
3 |
+
size 7640064
|
compiled/bc1b3efbe17382b052dc.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655eb5bb5ef10c66fc10131cbede36ff06d7d3f05633bd5023fbee1bcf0171a9
|
3 |
+
size 7681024
|
compiled/c13580424e448f3adb62.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d3345a258c792d64b5b732a2ef8d3ca1d483c991b110e6f876e98a129d0913
|
3 |
+
size 8459264
|
compiled/cd7da042b94df6a02f61.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48db029b385ad0c8af8c3d22562565e61043f96747de7ae137a0b282873daa93
|
3 |
+
size 7742464
|
compiled/d0dad260213be0bab13e.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3127242cd45689e7c0e45e892dc0e0d53420039cb98470916287b9ce92df56bb
|
3 |
+
size 7558144
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Mistral-7B-Instruct-v0.2/config.json",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"neuron": {
|
16 |
+
"auto_cast_type": "fp16",
|
17 |
+
"batch_size": 1,
|
18 |
+
"checkpoint_id": null,
|
19 |
+
"checkpoint_revision": null,
|
20 |
+
"compiler_type": "neuronx-cc",
|
21 |
+
"compiler_version": "2.12.68.0+4480452af",
|
22 |
+
"num_cores": 2,
|
23 |
+
"sequence_length": 2048,
|
24 |
+
"task": "text-generation"
|
25 |
+
},
|
26 |
+
"num_attention_heads": 32,
|
27 |
+
"num_hidden_layers": 32,
|
28 |
+
"num_key_value_heads": 8,
|
29 |
+
"rms_norm_eps": 1e-05,
|
30 |
+
"rope_theta": 1000000.0,
|
31 |
+
"sliding_window": 4096,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.36.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 32000
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|