Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
98bc9b4
•
1 Parent(s): 6831ed6

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/llama/m-a-p/OpenCodeInterpreter-DS-6.7B/158163e1ff79aab9a298.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1480,3 +1480,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_d713c0cfea83090fd469+2c2d707e/model.neff fi
1480
  neuronxcc-2.12.68.0+4480452af/MODULE_e919f8fb35a579ac8f04+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1481
  neuronxcc-2.12.68.0+4480452af/MODULE_afeac05aed21ad6d2f29+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1482
  neuronxcc-2.12.68.0+4480452af/MODULE_faaf9ba88c8c370df702+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1480
  neuronxcc-2.12.68.0+4480452af/MODULE_e919f8fb35a579ac8f04+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1481
  neuronxcc-2.12.68.0+4480452af/MODULE_afeac05aed21ad6d2f29+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1482
  neuronxcc-2.12.68.0+4480452af/MODULE_faaf9ba88c8c370df702+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1483
+ neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1484
+ neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/m-a-p/OpenCodeInterpreter-DS-6.7B/158163e1ff79aab9a298.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32256, "max_position_embeddings": 16384, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": false, "rope_theta": 100000, "rope_scaling": {"factor": 4.0, "type": "linear"}, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 32013, "eos_token_id": 32021, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "m-a-p/OpenCodeInterpreter-DS-6.7B", "checkpoint_revision": "60b89884df814590abd76757a6db4a527cbdfc91"}}
neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6356124ed504a695c1144f053f9782b49bc08a5ac596760e130d9ccfc22e5bf2
3
+ size 349423
neuronxcc-2.12.68.0+4480452af/MODULE_bb72ac50f29c80de2b1f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf4cbc6b19426779651a215d8df11ea86b563f248a716f8241c18595eb075d8
3
+ size 30628864
neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec6bb6c747cd76ae17034a7513858b6022de7004c311bb1888357e1f7363714
3
+ size 394266
neuronxcc-2.12.68.0+4480452af/MODULE_c4948d18f26f5b0e5378+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b801f73a64766836c9d1ef7c8c7a173dc8734d0772878090807e1aa11a1f8939
3
+ size 4496384