Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
8bc45df
•
1 Parent(s): d835aa0

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/meta-llama/Llama-2-7b-chat-hf/e8258490885b01bd2f24.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3485,3 +3485,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_ae09e83b659f98ea477e+2c2d707e/model.neff fi
3485
  neuronxcc-2.14.227.0+2d4f85be/MODULE_be1a181c8cb71942b5a2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3486
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ec64bbb632e94b829310+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3487
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0eedc6f1419de368b41+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3485
  neuronxcc-2.14.227.0+2d4f85be/MODULE_be1a181c8cb71942b5a2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3486
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ec64bbb632e94b829310+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3487
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0eedc6f1419de368b41+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3488
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3489
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/e8258490885b01bd2f24.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": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "f5db02db724555f92da89c216ac04704f23d4590", "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": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f56592a9bc61c0c87f81eba575af342c6308e54d63ab737beec6354d3163e2
3
+ size 336450
neuronxcc-2.14.227.0+2d4f85be/MODULE_22fe6bf779f1b27fe28d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff423e6cad3c0fe96cf740fab9f551975f89c1c1c65d775bb37ee4ffb8afebfa
3
+ size 12975104
neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe38e5692952aa2ff195e652464a76ac001a5fff0e11e998d6554a8f70191f9
3
+ size 434045
neuronxcc-2.14.227.0+2d4f85be/MODULE_8fd04fca310c9f1b4800+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06eae3c6d9b2748cad72de1cd5bcecf164670a3be27d1addcadaf26f57740063
3
+ size 9985024