Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
241
dacorvo HF staff commited on
Commit
21a5a17
•
1 Parent(s): cc3589a

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/mlabonne/AlphaMonarch-7B/f55b5ca4a9830e52e1a0.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1614,3 +1614,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_af59b6f0f7a58394cf61+2c2d707e/model.neff fi
1614
  neuronxcc-2.12.68.0+4480452af/MODULE_b7f50cac68e95c085768+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1615
  neuronxcc-2.12.68.0+4480452af/MODULE_38a909a9e66906ffe277+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1616
  neuronxcc-2.12.68.0+4480452af/MODULE_b1779304eead2fd6ef37+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
1615
  neuronxcc-2.12.68.0+4480452af/MODULE_38a909a9e66906ffe277+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1616
  neuronxcc-2.12.68.0+4480452af/MODULE_b1779304eead2fd6ef37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1617
+ neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1618
+ neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/mlabonne/AlphaMonarch-7B/f55b5ca4a9830e52e1a0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "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": "float16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "mlabonne/AlphaMonarch-7B", "checkpoint_revision": "c362a1b716189ecfcc311da08b5b873d0b964174"}}
neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ba80c1b3ee58bb8f92a9a7dda108857e9d771ab518197c371c5bbb04e65e5e
3
+ size 537246832
neuronxcc-2.12.68.0+4480452af/MODULE_21b6d22049a314e47f85+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b8fddb59d1047e2915606b6c783cf4547054b33f7433529eb0a03289871e29
3
+ size 113378304
neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120ac94f0f85ea23b61b69067f86d34d973ff4669e8a73469c0f346f5ca2f181
3
+ size 410840
neuronxcc-2.12.68.0+4480452af/MODULE_e61b509b122d3ae7ba02+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18085beea82b5d72ab0c5a785f81fc5f85b8b1bc10c68b2b6a601982984ee8b3
3
+ size 10732544