Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
255
dacorvo HF staff commited on
Commit
6dfddd1
•
1 Parent(s): 33ad62a

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/ibm/merlinite-7b/d75afbb08e31a407c42c.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3805,3 +3805,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_c74ba349a071b803bc47+2c2d707e/model.neff fi
3805
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0b7b9327c1a42d1b59e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3806
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f13a622b9ad1b70ff8c1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3807
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fb9f98125cbb6f56dd5d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3805
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0b7b9327c1a42d1b59e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3806
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f13a622b9ad1b70ff8c1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3807
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fb9f98125cbb6f56dd5d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3808
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3809
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/ibm/merlinite-7b/d75afbb08e31a407c42c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "end_token_id": 32000, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm/merlinite-7b", "checkpoint_revision": "233d12759d5bb9344231dafdb51310ec19d79c0e", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 32001, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32008}
neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1906ea6467e7fd34821ea13fb5cd445eed28358c002a3c854b5d0ed52f100827
3
+ size 537201436
neuronxcc-2.14.227.0+2d4f85be/MODULE_0bafc6247038d77534fe+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad4cc218e934b0712cddcd09d0234ad62dfd5b6a1fa02a6d673db65dd33dc3f
3
+ size 9298944
neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cdb2415fd20ef316b57c8ffe8d7dece013744a49bf96398662f96ebdc7cd193
3
+ size 360477
neuronxcc-2.14.227.0+2d4f85be/MODULE_d5b852336a4b8e589406+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7236dc658cd67fbc59e3e5c0a5dbc5ace494da4f685c0ce67d37661f44aec232
3
+ size 9104384