Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
255
dacorvo HF staff commited on
Commit
72eb49c
•
1 Parent(s): ea9ac3b

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/defog/sqlcoder-7b-2/d93fe38049979b3a11ec.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3631,3 +3631,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_93afc660e7e7f555747d+2c2d707e/model.neff fi
3631
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e2c7bb3483b611fefe7a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3632
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e9040de0b7ab62e09639+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3633
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ff563de6b8eaa289eed4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3631
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e2c7bb3483b611fefe7a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3632
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e9040de0b7ab62e09639+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3633
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ff563de6b8eaa289eed4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3634
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3635
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/defog/sqlcoder-7b-2/d93fe38049979b3a11ec.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "defog/sqlcoder-7b-2", "checkpoint_revision": "7e5b6f7981c0aa7d143f6bec6fa26625bdfcbe66", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32016}
neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c82f098850ddb1ba98da7c5ff29af38649055bab3213e64ac937fc1a4324f3
3
+ size 434045
neuronxcc-2.14.227.0+2d4f85be/MODULE_9b881381e74ef9d79023+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1a16e77c9bdd0f62833df46f42b82078554ab8ba1c36d4001c0af8cde5f9c0
3
+ size 9985024
neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c05a0849733c9b5a1c44ee9873a74b178ae569d2c6d9c03d92e60a0b60d01af
3
+ size 336450
neuronxcc-2.14.227.0+2d4f85be/MODULE_b0ee50055acc7160b489+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a805acc770b2b8cdbb8f18bb8f2e4d4f8eaf8804357620126696c154a57d5e6f
3
+ size 12995584