Synchronizing local compiler cache.
Browse files- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/mixtral/dacorvo/Mixtral-tiny/d722625ec9e7ce642ae3.json +41 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_06ca6d62f0361998714e+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_0a8fcf8ddb59d8730a24+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_226930e6ac9b200c488a+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_3f45d3caa2f3862b756d+613edded/model.neff +2 -2
- neuronxcc-2.17.194.0+d312836f/MODULE_8a11747c1cf643ac58ca+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_90381dde99583f54a60b+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_9ad3b35220e91074c83c+613edded/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_a7513d3ab2f1b0306086+613edded/model.neff +1 -1
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/mixtral/dacorvo/Mixtral-tiny/d722625ec9e7ce642ae3.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "dacorvo/Mixtral-tiny",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MixtralForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"head_dim": 32,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3584,
|
| 14 |
+
"max_position_embeddings": 1024,
|
| 15 |
+
"model_type": "mixtral",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast_type": "fp16",
|
| 18 |
+
"batch_size": 4,
|
| 19 |
+
"checkpoint_id": "dacorvo/Mixtral-tiny",
|
| 20 |
+
"checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
|
| 21 |
+
"compiler_type": "neuronx-cc",
|
| 22 |
+
"compiler_version": "2.17.194.0+d312836f",
|
| 23 |
+
"num_cores": 2,
|
| 24 |
+
"sequence_length": 1024,
|
| 25 |
+
"task": "text-generation"
|
| 26 |
+
},
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_experts_per_tok": 2,
|
| 29 |
+
"num_hidden_layers": 2,
|
| 30 |
+
"num_key_value_heads": 8,
|
| 31 |
+
"num_local_experts": 8,
|
| 32 |
+
"output_router_logits": false,
|
| 33 |
+
"rms_norm_eps": 1e-05,
|
| 34 |
+
"rope_theta": 10000.0,
|
| 35 |
+
"router_aux_loss_coef": 0.001,
|
| 36 |
+
"router_jitter_noise": 0.0,
|
| 37 |
+
"sliding_window": 4096,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 32000
|
| 41 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_06ca6d62f0361998714e+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 410624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4952737d9d85c255b42785472e6db9d374244b0bb4b000d4eff7296f0d41842
|
| 3 |
size 410624
|
neuronxcc-2.17.194.0+d312836f/MODULE_0a8fcf8ddb59d8730a24+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 410624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19bd02f71ae320954048c856327547b66c0a7e43ea2822f613145ddb3c0697ee
|
| 3 |
size 410624
|
neuronxcc-2.17.194.0+d312836f/MODULE_226930e6ac9b200c488a+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 441344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d46e13e892675ef4a0da5d1b9a20e55d0f3a66fd3260815ca63fe972965574f
|
| 3 |
size 441344
|
neuronxcc-2.17.194.0+d312836f/MODULE_3f45d3caa2f3862b756d+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62c674705b9318b5691e80fff22b816a1ea9f41d402d209dbae6832496bca803
|
| 3 |
+
size 1332224
|
neuronxcc-2.17.194.0+d312836f/MODULE_8a11747c1cf643ac58ca+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 472064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:209e211856db6808bd71233eb01275e3e6f2410f9e1d41088e63085374a31e47
|
| 3 |
size 472064
|
neuronxcc-2.17.194.0+d312836f/MODULE_90381dde99583f54a60b+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 431104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6fbd46a248636b45576ed5f043b62bbdc7f1941b74029671f3e21f7bbc2c0be
|
| 3 |
size 431104
|
neuronxcc-2.17.194.0+d312836f/MODULE_9ad3b35220e91074c83c+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 420864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9c5e174ed346b52da5e3d023e34df00eaa137d4e8a8c2bf3ccb30815a9b3db4
|
| 3 |
size 420864
|
neuronxcc-2.17.194.0+d312836f/MODULE_a7513d3ab2f1b0306086+613edded/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9b8f34c6801ac4d9e889365eb79ee734c781b523dc7a6f76765b24fb474359b
|
| 3 |
size 738304
|