Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
8644efd
•
1 Parent(s): c10d209

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/bc562327ccc495753228.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2364,3 +2364,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff fi
2364
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2365
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2366
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2364
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2365
  neuronxcc-2.13.66.0+6dfecc895/MODULE_4d9f16f5c3f401d9802e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2366
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d86cae1b9c06a97c4f5b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2367
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2368
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/bc562327ccc495753228.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "561487d18c41c76bcb5fc6cfb73a324982f04f47", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb4552f835e63fa2754ddad629dea199ec36a3302958ef7ad985acde8d2de05
3
+ size 345998
neuronxcc-2.13.66.0+6dfecc895/MODULE_152f1d3a545af4cf114d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852916803c80a18dadb5e5c216400d61d78f4f8b31b23eb797b46cd77695e22e
3
+ size 30669824
neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79635082f4bd962ad53d2103a70e25124b49b40545d1d4e9a4564b4bc598e00
3
+ size 399354
neuronxcc-2.13.66.0+6dfecc895/MODULE_dca6e0cd7c3f5f84095d+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ec2223a8d49e5e8084f06d1bed8beabd8f00428e375b1299e696bd144982d2
3
+ size 3462144