Synchronizing local compiler cache.
Browse files- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/11e18115af2cd459e483.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/15e8c952b3c81fd87a57.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/25d78386bf1607f07ae3.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/3172e154191b4ca8bee2.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/348c549d4253f4d0d1e3.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/443c93e614cf44693e97.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/66bbed419fdfeaab3c6f.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/918314d480c5f9760153.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/bcce81dc6dcb5f751067.json +1 -0
- neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/c7396366ada80bbdba9a.json +1 -0
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/11e18115af2cd459e483.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/15e8c952b3c81fd87a57.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/25d78386bf1607f07ae3.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/3172e154191b4ca8bee2.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/348c549d4253f4d0d1e3.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/443c93e614cf44693e97.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/66bbed419fdfeaab3c6f.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 8, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/918314d480c5f9760153.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 8, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/bcce81dc6dcb5f751067.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/c7396366ada80bbdba9a.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
|