Synchronizing local compiler cache.
Browse files- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/789b5d4a7bdfd905877f.json +58 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4582709e56c629d9c464.json +62 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/a26633219d7308901cb9.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/1ac5416e0e8a986447af.json +81 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/ff29855d6e6a0e6e89ea.json +58 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/1d198d134b6736b8c253.json +59 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/71aae2feb728a4bc1bea.json +64 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/77a592cfa3aea3ceb6ea.json +65 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_50d30ce495feb34fe5c1+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_50d30ce495feb34fe5c1+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_73b50e8e61409e1f8fe1+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_73b50e8e61409e1f8fe1+ed72d204/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_cae14ab78f54c8b4e73f+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_cae14ab78f54c8b4e73f+ed72d204/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff +1 -1
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/789b5d4a7bdfd905877f.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attention_multiplier": 1.0,
|
| 11 |
+
"embedding_multiplier": 1.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 32,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 64,
|
| 16 |
+
"logits_scaling": 1.0,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 1,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
|
| 25 |
+
"checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
|
| 26 |
+
"continuous_batching": false,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"max_batch_size": 1,
|
| 33 |
+
"max_context_length": 1024,
|
| 34 |
+
"max_topk": 256,
|
| 35 |
+
"n_active_tokens": 1024,
|
| 36 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 37 |
+
"on_device_sampling": true,
|
| 38 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 39 |
+
"output_logits": false,
|
| 40 |
+
"pp_degree": 1,
|
| 41 |
+
"sequence_length": 1024,
|
| 42 |
+
"speculation_length": 0,
|
| 43 |
+
"start_rank_id": 0,
|
| 44 |
+
"target": "trn1",
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"tp_degree": 2
|
| 47 |
+
},
|
| 48 |
+
"num_attention_heads": 4,
|
| 49 |
+
"num_hidden_layers": 2,
|
| 50 |
+
"num_key_value_heads": 4,
|
| 51 |
+
"residual_multiplier": 1.0,
|
| 52 |
+
"rms_norm_eps": 1e-06,
|
| 53 |
+
"rope_scaling": null,
|
| 54 |
+
"rope_theta": 10000.0,
|
| 55 |
+
"tie_word_embeddings": false,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 49152
|
| 58 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4582709e56c629d9c464.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"max_batch_size": 1,
|
| 31 |
+
"max_context_length": 1024,
|
| 32 |
+
"max_topk": 256,
|
| 33 |
+
"n_active_tokens": 1024,
|
| 34 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 35 |
+
"on_device_sampling": true,
|
| 36 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 37 |
+
"output_logits": false,
|
| 38 |
+
"pp_degree": 1,
|
| 39 |
+
"sequence_length": 1024,
|
| 40 |
+
"speculation_length": 0,
|
| 41 |
+
"start_rank_id": 0,
|
| 42 |
+
"target": "trn1",
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"tp_degree": 2
|
| 45 |
+
},
|
| 46 |
+
"num_attention_heads": 4,
|
| 47 |
+
"num_hidden_layers": 2,
|
| 48 |
+
"num_key_value_heads": 4,
|
| 49 |
+
"pretraining_tp": 1,
|
| 50 |
+
"rms_norm_eps": 1e-05,
|
| 51 |
+
"rope_scaling": {
|
| 52 |
+
"factor": 8.0,
|
| 53 |
+
"high_freq_factor": 4.0,
|
| 54 |
+
"low_freq_factor": 1.0,
|
| 55 |
+
"original_max_position_embeddings": 8192,
|
| 56 |
+
"rope_type": "llama3"
|
| 57 |
+
},
|
| 58 |
+
"rope_theta": 500000.0,
|
| 59 |
+
"tie_word_embeddings": false,
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 128256
|
| 62 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/a26633219d7308901cb9.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 23 |
+
"checkpoint_revision": null,
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": false,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"max_batch_size": 1,
|
| 31 |
+
"max_context_length": 4096,
|
| 32 |
+
"max_topk": 256,
|
| 33 |
+
"n_active_tokens": 4096,
|
| 34 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 35 |
+
"on_device_sampling": false,
|
| 36 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 37 |
+
"output_logits": false,
|
| 38 |
+
"pp_degree": 1,
|
| 39 |
+
"sequence_length": 4096,
|
| 40 |
+
"speculation_length": 5,
|
| 41 |
+
"start_rank_id": 0,
|
| 42 |
+
"target": "trn1",
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"tp_degree": 2
|
| 45 |
+
},
|
| 46 |
+
"num_attention_heads": 32,
|
| 47 |
+
"num_hidden_layers": 16,
|
| 48 |
+
"num_key_value_heads": 8,
|
| 49 |
+
"pretraining_tp": 1,
|
| 50 |
+
"rms_norm_eps": 1e-05,
|
| 51 |
+
"rope_scaling": {
|
| 52 |
+
"factor": 32.0,
|
| 53 |
+
"high_freq_factor": 4.0,
|
| 54 |
+
"low_freq_factor": 1.0,
|
| 55 |
+
"original_max_position_embeddings": 8192,
|
| 56 |
+
"rope_type": "llama3"
|
| 57 |
+
},
|
| 58 |
+
"rope_theta": 500000.0,
|
| 59 |
+
"tie_word_embeddings": true,
|
| 60 |
+
"unsloth_fixed": true,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/1ac5416e0e8a986447af.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "tiny-random/llama-4",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_chunk_size": 128,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_scale": 0.1,
|
| 9 |
+
"attn_temperature_tuning": 4,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
+
"floor_scale": 8192,
|
| 12 |
+
"for_llm_compressor": false,
|
| 13 |
+
"head_dim": 32,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 32,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"interleave_moe_layer_step": 2,
|
| 18 |
+
"intermediate_size": 64,
|
| 19 |
+
"intermediate_size_mlp": 128,
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"chunked_attention",
|
| 22 |
+
"chunked_attention",
|
| 23 |
+
"chunked_attention",
|
| 24 |
+
"full_attention"
|
| 25 |
+
],
|
| 26 |
+
"max_position_embeddings": 1048576,
|
| 27 |
+
"model_type": "llama4_text",
|
| 28 |
+
"moe_layers": [
|
| 29 |
+
1,
|
| 30 |
+
3
|
| 31 |
+
],
|
| 32 |
+
"neuron": {
|
| 33 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 34 |
+
"batch_size": 1,
|
| 35 |
+
"capacity_factor": null,
|
| 36 |
+
"checkpoint_id": "tiny-random/llama-4",
|
| 37 |
+
"checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4",
|
| 38 |
+
"continuous_batching": false,
|
| 39 |
+
"enable_bucketing": false,
|
| 40 |
+
"ep_degree": 1,
|
| 41 |
+
"fused_qkv": false,
|
| 42 |
+
"glu_mlp": true,
|
| 43 |
+
"local_ranks_size": 2,
|
| 44 |
+
"max_batch_size": 1,
|
| 45 |
+
"max_context_length": 1024,
|
| 46 |
+
"max_topk": 256,
|
| 47 |
+
"n_active_tokens": 1024,
|
| 48 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 49 |
+
"on_device_sampling": true,
|
| 50 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 51 |
+
"output_logits": false,
|
| 52 |
+
"pp_degree": 1,
|
| 53 |
+
"sequence_length": 1024,
|
| 54 |
+
"speculation_length": 0,
|
| 55 |
+
"start_rank_id": 0,
|
| 56 |
+
"target": "trn1",
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
+
"tp_degree": 2
|
| 59 |
+
},
|
| 60 |
+
"no_rope_layers": [
|
| 61 |
+
1,
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
0
|
| 65 |
+
],
|
| 66 |
+
"num_attention_heads": 1,
|
| 67 |
+
"num_experts_per_tok": 1,
|
| 68 |
+
"num_hidden_layers": 4,
|
| 69 |
+
"num_key_value_heads": 1,
|
| 70 |
+
"num_local_experts": 8,
|
| 71 |
+
"output_router_logits": false,
|
| 72 |
+
"rms_norm_eps": 1e-05,
|
| 73 |
+
"rope_scaling": null,
|
| 74 |
+
"rope_theta": 500000.0,
|
| 75 |
+
"router_aux_loss_coef": 0.001,
|
| 76 |
+
"router_jitter_noise": 0.0,
|
| 77 |
+
"tie_word_embeddings": true,
|
| 78 |
+
"use_cache": true,
|
| 79 |
+
"use_qk_norm": true,
|
| 80 |
+
"vocab_size": 202048
|
| 81 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/ff29855d6e6a0e6e89ea.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 18 |
+
"batch_size": 1,
|
| 19 |
+
"capacity_factor": null,
|
| 20 |
+
"checkpoint_id": "dacorvo/Mixtral-tiny",
|
| 21 |
+
"checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
|
| 22 |
+
"continuous_batching": false,
|
| 23 |
+
"enable_bucketing": false,
|
| 24 |
+
"ep_degree": 1,
|
| 25 |
+
"fused_qkv": false,
|
| 26 |
+
"glu_mlp": true,
|
| 27 |
+
"local_ranks_size": 2,
|
| 28 |
+
"max_batch_size": 1,
|
| 29 |
+
"max_context_length": 1024,
|
| 30 |
+
"max_topk": 256,
|
| 31 |
+
"n_active_tokens": 1024,
|
| 32 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 33 |
+
"on_device_sampling": false,
|
| 34 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 35 |
+
"output_logits": false,
|
| 36 |
+
"pp_degree": 1,
|
| 37 |
+
"sequence_length": 1024,
|
| 38 |
+
"speculation_length": 0,
|
| 39 |
+
"start_rank_id": 0,
|
| 40 |
+
"target": "trn1",
|
| 41 |
+
"torch_dtype": "bfloat16",
|
| 42 |
+
"tp_degree": 2
|
| 43 |
+
},
|
| 44 |
+
"num_attention_heads": 32,
|
| 45 |
+
"num_experts_per_tok": 2,
|
| 46 |
+
"num_hidden_layers": 2,
|
| 47 |
+
"num_key_value_heads": 8,
|
| 48 |
+
"num_local_experts": 8,
|
| 49 |
+
"output_router_logits": false,
|
| 50 |
+
"rms_norm_eps": 1e-05,
|
| 51 |
+
"rope_theta": 10000.0,
|
| 52 |
+
"router_aux_loss_coef": 0.001,
|
| 53 |
+
"router_jitter_noise": 0.0,
|
| 54 |
+
"sliding_window": 4096,
|
| 55 |
+
"tie_word_embeddings": false,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 32000
|
| 58 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/1d198d134b6736b8c253.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "yujiepan/phi-4-tiny-random",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {},
|
| 11 |
+
"embd_pdrop": 0.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 16,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 32,
|
| 16 |
+
"max_position_embeddings": 16384,
|
| 17 |
+
"model_type": "phi3",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "yujiepan/phi-4-tiny-random",
|
| 23 |
+
"checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"max_batch_size": 1,
|
| 31 |
+
"max_context_length": 1024,
|
| 32 |
+
"max_topk": 256,
|
| 33 |
+
"n_active_tokens": 1024,
|
| 34 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 35 |
+
"on_device_sampling": true,
|
| 36 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 37 |
+
"output_logits": false,
|
| 38 |
+
"pp_degree": 1,
|
| 39 |
+
"sequence_length": 1024,
|
| 40 |
+
"speculation_length": 0,
|
| 41 |
+
"start_rank_id": 0,
|
| 42 |
+
"target": "trn1",
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"tp_degree": 2
|
| 45 |
+
},
|
| 46 |
+
"num_attention_heads": 2,
|
| 47 |
+
"num_hidden_layers": 2,
|
| 48 |
+
"num_key_value_heads": 1,
|
| 49 |
+
"original_max_position_embeddings": 16384,
|
| 50 |
+
"partial_rotary_factor": 1.0,
|
| 51 |
+
"resid_pdrop": 0.0,
|
| 52 |
+
"rms_norm_eps": 1e-05,
|
| 53 |
+
"rope_scaling": null,
|
| 54 |
+
"rope_theta": 250000,
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 100352
|
| 59 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/71aae2feb728a4bc1bea.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "yujiepan/qwen2.5-128k-tiny-random",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 8,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 16,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention"
|
| 16 |
+
],
|
| 17 |
+
"max_position_embeddings": 32768,
|
| 18 |
+
"max_window_layers": 1,
|
| 19 |
+
"model_type": "qwen2",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 1,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
|
| 25 |
+
"checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
|
| 26 |
+
"continuous_batching": false,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": false,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"max_batch_size": 1,
|
| 33 |
+
"max_context_length": 1024,
|
| 34 |
+
"max_topk": 256,
|
| 35 |
+
"n_active_tokens": 1024,
|
| 36 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 37 |
+
"on_device_sampling": true,
|
| 38 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 39 |
+
"output_logits": false,
|
| 40 |
+
"pp_degree": 1,
|
| 41 |
+
"sequence_length": 1024,
|
| 42 |
+
"speculation_length": 0,
|
| 43 |
+
"start_rank_id": 0,
|
| 44 |
+
"target": "trn1",
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"tp_degree": 2
|
| 47 |
+
},
|
| 48 |
+
"num_attention_heads": 4,
|
| 49 |
+
"num_hidden_layers": 2,
|
| 50 |
+
"num_key_value_heads": 2,
|
| 51 |
+
"rms_norm_eps": 1e-06,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 4.0,
|
| 54 |
+
"original_max_position_embeddings": 32768,
|
| 55 |
+
"rope_type": "yarn",
|
| 56 |
+
"type": "yarn"
|
| 57 |
+
},
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"sliding_window": null,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"use_sliding_window": false,
|
| 63 |
+
"vocab_size": 152064
|
| 64 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/77a592cfa3aea3ceb6ea.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "optimum-internal-testing/tiny-random-qwen3_moe",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3MoeForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"decoder_sparse_step": 2,
|
| 11 |
+
"head_dim": 32,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 64,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 128,
|
| 16 |
+
"max_position_embeddings": 40960,
|
| 17 |
+
"max_window_layers": 1,
|
| 18 |
+
"mlp_only_layers": [],
|
| 19 |
+
"model_type": "qwen3_moe",
|
| 20 |
+
"moe_intermediate_size": 128,
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 1,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe",
|
| 26 |
+
"checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af",
|
| 27 |
+
"continuous_batching": false,
|
| 28 |
+
"enable_bucketing": false,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": false,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"max_batch_size": 1,
|
| 34 |
+
"max_context_length": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.4.1.dev0",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"sequence_length": 1024,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": "trn1",
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"norm_topk_prob": true,
|
| 50 |
+
"num_attention_heads": 2,
|
| 51 |
+
"num_experts": 8,
|
| 52 |
+
"num_experts_per_tok": 2,
|
| 53 |
+
"num_hidden_layers": 2,
|
| 54 |
+
"num_key_value_heads": 1,
|
| 55 |
+
"output_router_logits": false,
|
| 56 |
+
"rms_norm_eps": 1e-06,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 1000000.0,
|
| 59 |
+
"router_aux_loss_coef": 0.001,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"use_sliding_window": false,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be474cdb3dee1b28b0f2c4a3b2f352e571cf3a468cfdbefd0c6adb39b351d32e
|
| 3 |
size 246784
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 255104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba6e863951076186e55b60309ad403bef45b8cdf8ae435cfea24baed3501ff50
|
| 3 |
size 255104
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 90382
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02600675cb7c8ca5d1f2075830e8debc6e9695a82feca2066bb6bef97a44a512
|
| 3 |
size 90382
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 359424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e14327d2f51da405e88b30418db0c11bb9debf3521db564b5856377ecf8c9971
|
| 3 |
size 359424
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3093504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70d650de28d7b13defbb5f9d78b06f99ec63ba26cda803845b298cbca3d0581
|
| 3 |
size 3093504
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3167748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d0d1b1e40a092a3eec560354aeb1191196e8b39c2312249a4d6f358c7ef2a51
|
| 3 |
size 3167748
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_50d30ce495feb34fe5c1+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1926144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af93b3d02b40084bdec001a9496f6b98115e3bfebad2f126075400a4c60fbd87
|
| 3 |
size 1926144
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_50d30ce495feb34fe5c1+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2082478
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6951f83519dce668f7723834939eacc71fdb113475631340f061d1db9cd51852
|
| 3 |
size 2082478
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 86123
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78e20990397e5c1575c52a54fc1745be85c4f7f901a1e8fbb3b5827a694bf4a5
|
| 3 |
size 86123
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 257024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb04001e482d00a4af5fb97f6bcc1c96216d7da0ec4a5998a0e7a9d26677b43e
|
| 3 |
size 257024
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_73b50e8e61409e1f8fe1+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 509252
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:441fac3e96e30c894231d7f6dd20d4e89e6b4cf1295ed681a96fb69af4ea7582
|
| 3 |
size 509252
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_73b50e8e61409e1f8fe1+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41585664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccfc71e4eaf13a28e93ac88d5f63f2d222b919a9db2e9f4a966422a8f787f591
|
| 3 |
size 41585664
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 543744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40ffa4c2b1a8bd699eabd5c72a80b84ed771f0105eced55f7b9b13da8aeb8391
|
| 3 |
size 543744
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 563380
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093f2c67a771901b8ca6efd4cc10914b71b3bc2274c5047aa923491c5fca89d0
|
| 3 |
size 563380
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 277504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3df3cf6d998ee655a4ab528b086e3fd141717662a93fa0050345ebc65767d331
|
| 3 |
size 277504
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 289031
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3269c2c8f12aa76fc71cb4442d2a32596b20e46841a799b466b3f1504ad2db13
|
| 3 |
size 289031
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_cae14ab78f54c8b4e73f+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 739366
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8511b22bc58244c0086580ec7d72532553a8f93a374268bdb1fbb737acfc3a4
|
| 3 |
size 739366
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_cae14ab78f54c8b4e73f+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 26133504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb3d7bc9903f8346667ae3bc452aa306ed217fe3fc73cd25365d476c98eac8
|
| 3 |
size 26133504
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 216064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6de0cdcccde4d6c5b6085c4917bd8e56006f681001b70115d51bddbadc87a08d
|
| 3 |
size 216064
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 224412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6132f4336e6fa21ad6c9e001154bce4af1a00572183fcbb8251e7c2e5bf92b3a
|
| 3 |
size 224412
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 82772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec6b5d749ba16b2de638bf1df7431fe2e43da05aa54851f276d7647ba88c5d5
|
| 3 |
size 82772
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4eef61e2c1dff014888bee516c930535f9079d5594e478edc9c4eade7026c12
|
| 3 |
size 267264
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 694128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8cea1685d29853d3461b266fc7630a02c24397d66e3896bed5b3cdedb728876
|
| 3 |
size 694128
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 625664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac903b6b4a5cc5d3c9f923db50534efd2212faf0a366a3578200f63e564d83f1
|
| 3 |
size 625664
|