Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
dd7c401
•
1 Parent(s): cea6432

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/mistralai/Mistral-7B-Instruct-v0.3/bda526e2d35c344d79a5.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3579,3 +3579,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.neff fi
3579
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3580
  neuronxcc-2.14.227.0+2d4f85be/MODULE_0633bed8dd5b2f659fd4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3581
  neuronxcc-2.14.227.0+2d4f85be/MODULE_551ac88dc576f8ceff79+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3579
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3580
  neuronxcc-2.14.227.0+2d4f85be/MODULE_0633bed8dd5b2f659fd4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3581
  neuronxcc-2.14.227.0+2d4f85be/MODULE_551ac88dc576f8ceff79+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3582
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3583
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/bda526e2d35c344d79a5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "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": "fp16", "batch_size": 32, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "708a0609e640ac1edfb9020a7c934f51d34d6c79", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cc6a426ed2173b3aecf7d820de1df5207e516be3385cf95f56ea2b05de0de1
3
+ size 307162
neuronxcc-2.14.227.0+2d4f85be/MODULE_3e753982d2ae97234d73+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658ec555e5141e45c9ff7410f9a2c0b98d61596f5a6ed204c772ec6fd964caac
3
+ size 30802944
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bcad41427aaa4d12ab94bdac700c777e50518fd9059a3e4d3519c77951cca3
3
+ size 360349
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f8bfd278d08c2ff7c19+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47088a82f6373da8d1e17b87f31d0935f8e69bec3892d085417feb52b1733cad
3
+ size 5622784