Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
e6e2c33
·
verified ·
1 Parent(s): 12442c4

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/10407adf76187d65baed.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7137,3 +7137,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_b22e2f5845207f7f190e+613edded/model.neff fi
7137
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b73b1eaea0f6f5dfe7f3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7138
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c299f9936437dd67f341+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7139
  neuronxcc-2.16.372.0+4a9b2326/MODULE_ff8fad012e7766ca23ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7137
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b73b1eaea0f6f5dfe7f3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7138
  neuronxcc-2.16.372.0+4a9b2326/MODULE_c299f9936437dd67f341+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7139
  neuronxcc-2.16.372.0+4a9b2326/MODULE_ff8fad012e7766ca23ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7140
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7141
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/10407adf76187d65baed.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "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-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e188ed182cf535a8d1e822d7948bcb9af6f9a10a012e35006324f6569131bf
3
+ size 363550
neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390b3462b46535c6bd49fb064dbab5dfc0d40e8ef993342d67c3595bf6c2db31
3
+ size 8735744
neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2effee9d1ea384aa94a0acaf4391f9e26d7248bccd359fc89d4fb06455d1f9d
3
+ size 302074
neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1908f4839059173c18c5dc8667233596a9e13954af9336df3f01fe53c8c3371f
3
+ size 5919744