Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
236
dacorvo HF staff commited on
Commit
3d41042
•
1 Parent(s): bda414f

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/NousResearch/Hermes-2-Pro-Mistral-7B/f6f720a063bd0c949f2c.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1596,3 +1596,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_887b086eed744e070ce3+2c2d707e/model.neff fi
1596
  neuronxcc-2.12.68.0+4480452af/MODULE_c8f83c84f5e20d19218f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1597
  neuronxcc-2.12.68.0+4480452af/MODULE_cefe91c9d3c2e5ed5158+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1598
  neuronxcc-2.12.68.0+4480452af/MODULE_f4cb004f57682ffa94f9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1596
  neuronxcc-2.12.68.0+4480452af/MODULE_c8f83c84f5e20d19218f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1597
  neuronxcc-2.12.68.0+4480452af/MODULE_cefe91c9d3c2e5ed5158+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1598
  neuronxcc-2.12.68.0+4480452af/MODULE_f4cb004f57682ffa94f9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1599
+ neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1600
+ neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/NousResearch/Hermes-2-Pro-Mistral-7B/f6f720a063bd0c949f2c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32032, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": false, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 32000, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Hermes-2-Pro-Mistral-7B", "checkpoint_revision": "4d50786bb33ce7c31697932a0ebe01fd8a373a4a"}}
neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0375baee997386763c5113e6fe590ce8e5af263955eaaae609993bf33dca20d
3
+ size 537246832
neuronxcc-2.12.68.0+4480452af/MODULE_380e58f62866490411be+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ae60663d70643b0f1b8a03ea5f141fce330b4ab14fb93e902bfbf6b15266ad
3
+ size 113470464
neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f4671dd9879314bf040de6438ea1f5676e47ad38bbff1a788f5682af3cd3c5
3
+ size 410840
neuronxcc-2.12.68.0+4480452af/MODULE_f87d8d4cd224b40af548+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe89780f38abfff4bcc63b9f0c1d062a92b4e3255b0b505a58e910b7627a215
3
+ size 10732544