Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
9f67bfd
•
1 Parent(s): 6cffe87

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/ibm/merlinite-7b/8fb7463ba3b1b70a919c.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1610,3 +1610,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_ce8644fcb54c67a894fa+2c2d707e/model.neff fi
1610
  neuronxcc-2.12.68.0+4480452af/MODULE_d2b63d1738b927eee418+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1611
  neuronxcc-2.12.68.0+4480452af/MODULE_d6428e02b616d614799a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1612
  neuronxcc-2.12.68.0+4480452af/MODULE_d7a487747eb6a744594e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1610
  neuronxcc-2.12.68.0+4480452af/MODULE_d2b63d1738b927eee418+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1611
  neuronxcc-2.12.68.0+4480452af/MODULE_d6428e02b616d614799a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1612
  neuronxcc-2.12.68.0+4480452af/MODULE_d7a487747eb6a744594e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1613
+ neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1614
+ neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/ibm/merlinite-7b/8fb7463ba3b1b70a919c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32008, "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": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "pad_token_id": 32001, "eos_token_id": 2, "end_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": "ibm/merlinite-7b", "checkpoint_revision": "233d12759d5bb9344231dafdb51310ec19d79c0e"}}
neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c096be1b15969cd2ad2d2b537f8944f8256f5b976728746d6a671c43f782c7
3
+ size 410840
neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd80b084c24c1167fd901127b0f42909f08ea80171950c921f4bf177067ace2
3
+ size 10732544
neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cd9d5fb91929e02cb5417e8e5d50ef661389ffe05148cbf5a31ad776d0d861
3
+ size 537246832
neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4666ada56652adf4de93e4c3fe383e72a9e701ff80529aa6a1c5e2bdd77db6b0
3
+ size 113449984