Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
239
dacorvo HF staff commited on
Commit
28f3bad
•
1 Parent(s): 290b0f7

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/01-ai/Yi-34B-200K/03153a430703cb2715ad.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2995,3 +2995,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_d65d648ba2d719a89f20+2c2d707e/model.neff fi
2995
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e47e20d8aa2b6e1ba845+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2996
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e55b4e7d808bbaf9f1a9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2997
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea31894e874a6024428e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2995
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e47e20d8aa2b6e1ba845+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2996
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e55b4e7d808bbaf9f1a9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2997
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ea31894e874a6024428e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2998
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2999
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/llama/01-ai/Yi-34B-200K/03153a430703cb2715ad.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": 7168, "initializer_range": 0.02, "intermediate_size": 20480, "max_position_embeddings": 200000, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "01-ai/Yi-34B-200K", "checkpoint_revision": "86c47358905adfe06b8c39d8f9adcbcfda3b51ad", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 56, "num_hidden_layers": 60, "num_key_value_heads": 8, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 64000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe286114134c07a2719cf3ab6909193d778e47f9728c273c8bc73cbbe803cf70
3
+ size 716570
neuronxcc-2.13.66.0+6dfecc895/MODULE_51908aacfbf851d85af4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f62c30bc8cf602e2bf9f59717ae5524f86ac343a3a7306ab1e82a0700dd19a
3
+ size 9227264
neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231287d1610a0f428c1e6279e6f56e743da7601b975be4cc1e6e76b50a316a10
3
+ size 631113
neuronxcc-2.13.66.0+6dfecc895/MODULE_cef8491fe79ba64897ec+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b692636943ce053c668d74522445070df2acfa9ec816bc053bf283322ec96fc
3
+ size 9421824