Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
optimum-internal-testing-user commited on
Commit
57d3965
·
verified ·
1 Parent(s): 31dfaae

Synchronizing local compiler cache.

Browse files
Files changed (9) hide show
  1. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6f5a57eff96603155de0.json +81 -0
  2. neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/model.neff +1 -1
  3. neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/wrapped_neff.hlo +1 -1
  4. neuronxcc-2.21.33363.0+82129205/MODULE_958d41f716f615f7fb01+24129607/model.neff +1 -1
  5. neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/model.hlo_module.pb +1 -1
  6. neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/model.neff +1 -1
  7. neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/wrapped_neff.hlo +1 -1
  8. neuronxcc-2.21.33363.0+82129205/MODULE_e45e2c512692918b8ac7+24129607/model.hlo_module.pb +1 -1
  9. neuronxcc-2.21.33363.0+82129205/MODULE_e45e2c512692918b8ac7+24129607/model.neff +1 -1
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6f5a57eff96603155de0.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/gemma-3-270m-it",
4
+ "_sliding_window_pattern": 6,
5
+ "_task": "text-generation",
6
+ "architectures": [
7
+ "Gemma3ForCausalLM"
8
+ ],
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_logit_softcapping": null,
12
+ "dtype": "bfloat16",
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 640,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2048,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "model_type": "gemma3_text",
41
+ "neuron": {
42
+ "_serialized_key": "NxDNeuronConfig",
43
+ "batch_size": 1,
44
+ "capacity_factor": null,
45
+ "checkpoint_id": "unsloth/gemma-3-270m-it",
46
+ "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9",
47
+ "continuous_batching": false,
48
+ "ep_degree": 1,
49
+ "fused_qkv": true,
50
+ "glu_mlp": true,
51
+ "local_ranks_size": 2,
52
+ "max_batch_size": 1,
53
+ "max_context_length": 8192,
54
+ "max_topk": 256,
55
+ "n_active_tokens": 8192,
56
+ "neuronxcc_version": "2.21.33363.0+82129205",
57
+ "on_device_sampling": true,
58
+ "optimum_neuron_version": "0.4.6.dev0",
59
+ "output_logits": false,
60
+ "pp_degree": 1,
61
+ "sequence_length": 8192,
62
+ "speculation_length": 0,
63
+ "start_rank_id": 0,
64
+ "target": "trn1",
65
+ "torch_dtype": "bfloat16",
66
+ "tp_degree": 2
67
+ },
68
+ "num_attention_heads": 4,
69
+ "num_hidden_layers": 18,
70
+ "num_key_value_heads": 1,
71
+ "query_pre_attn_scalar": 256,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_local_base_freq": 10000.0,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 512,
77
+ "unsloth_fixed": true,
78
+ "use_bidirectional_attention": false,
79
+ "use_cache": true,
80
+ "vocab_size": 262144
81
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fb03f488c92436029188312487408635c6f48b2e8ed404968c7078dcc2fa6f4
3
  size 1373184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cdc4e858377a179e32b2566e433818bdf91ddda5ddfe5151dc0e78101c9066b
3
  size 1373184
neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6688e677e3117405b9330d389599bc8c0f04f35b20c46be77564486c7c292575
3
  size 1495573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee85311c9e3891aa28d60adf06ff5fbc80d7036133daffe4922823d320286cb
3
  size 1495573
neuronxcc-2.21.33363.0+82129205/MODULE_958d41f716f615f7fb01+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b7a77cac55c8ec5f8af5c9517254443a64301cda8b3d8eabb38d14e07adbe8
3
  size 29942784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa81b8f7bcb32c5911e3bd7fe5883d54ba8e6da6cf13e02c30b845d91f9d37de
3
  size 29942784
neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66f6450490b10388dafb6e4fb250f49f37b11224dd2e5c49f481a0976f729106
3
  size 562167
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedde36e9447943a3efdf4ed22ba8e8377c18dc164c05dc9ec3b2404fd285d6c
3
  size 562167
neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac673781bbf3e2dbc475872bf420164d20d0771203247969452879b64ad49b1f
3
  size 1793024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b19d16e87edce0eb519472854464ea428c8c6621ce680463c7a0576186d64b
3
  size 1793024
neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:794b24bed8dc827a4275a8e1acbadd1ec8b9d25d8643b83854e9dfaa4b94f296
3
  size 1915413
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4364f3e30295be20e1b36a9f8b3877323fbdd44fe0154ef2aa2e7e559a991578
3
  size 1915413
neuronxcc-2.21.33363.0+82129205/MODULE_e45e2c512692918b8ac7+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:709aef187eaab30b99967d754304fe6bf08161b2e4820c8d294053c66f68c8ae
3
  size 571822
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09002100cbee99f3cf9d355464c3b373418336fa7f26fce3379b075a8ff4dd8b
3
  size 571822
neuronxcc-2.21.33363.0+82129205/MODULE_e45e2c512692918b8ac7+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0946eccda0ccaa11fd83c9e6b1926be6d653f863251c91dca40ee872de00538
3
  size 9503744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94048b1e583bea84cb9e311cfe1f6298e201e617dedcd340fbc12ea64ab735d
3
  size 9503744