Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
147
dacorvo HF staff commited on
Commit
61bde38
•
1 Parent(s): 57652e6

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/9567187dc1f707d3f2b5.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3180,3 +3180,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_bf49580423129e50f96d+2c2d707e/model.neff fi
3180
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c129045bda9bf853b93e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3181
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ccdbae5eeb030e72d5cf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f4f63b2510413deb054c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3180
  neuronxcc-2.13.66.0+6dfecc895/MODULE_c129045bda9bf853b93e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3181
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ccdbae5eeb030e72d5cf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f4f63b2510413deb054c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3183
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3184
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/9567187dc1f707d3f2b5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MixtralForCausalLM"], "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": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "checkpoint_revision": "1e637f2d7cb0a9d6fb1922f305cb784995190a83", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26ec48a624f902d0ae48e2caebb0568aa6c7a49f12bcc934de2e89f5bb3ef5f
3
+ size 505434
neuronxcc-2.13.66.0+6dfecc895/MODULE_2e3955295809c3fe96ec+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b3c1d109eb51087bf90df518de33830bbc5bf3d40d83289a4f72749d5fce9c
3
+ size 5643264
neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b72aee781d272153a023dbfa7cd761513d2b7332da614bf38ac1e2a3f1222f
3
+ size 461360
neuronxcc-2.13.66.0+6dfecc895/MODULE_79c2345da3e40d137cdb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6e2996e57f0f60fcf23fca1b6bc302248f2e52c661742fbf54c249be9e2146
3
+ size 8397824