Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
268
dacorvo HF staff commited on
Commit
d7abc33
•
1 Parent(s): ae5e65a

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/15e8c952b3c81fd87a57.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1068,3 +1068,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_c87736fc8d652bb9115d+2c2d707e/model.neff fi
1068
  neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1069
  neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1070
  neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1068
  neuronxcc-2.12.68.0+4480452af/MODULE_dae64c7e2fea06ef54cc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1069
  neuronxcc-2.12.68.0+4480452af/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1070
  neuronxcc-2.12.68.0+4480452af/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1071
+ neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1072
+ neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/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/MODULE_3db0ad40efa03140e160+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8dccd83aaa846642652c901b179b69ccce86369a5a4c8139ff3e6a18d69835
3
+ size 350447
neuronxcc-2.12.68.0+4480452af/MODULE_3db0ad40efa03140e160+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da95834efd9891111745c1b59125070dc9a5d06d3bd4e2c2d8305311e62ed87c
3
+ size 18842624
neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4247cd8a4c74da237038adabe9de49c52639e9da42ebe3c1d02fadbf8bcc8e2
3
+ size 395290
neuronxcc-2.12.68.0+4480452af/MODULE_b69f156f424e6ed5f284+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe2d4d3e920e7cccf9dc35a40d8fcef8e8e085ba410e9f8047b69a94b1e020c
3
+ size 2386944