Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
9228643
·
verified ·
1 Parent(s): 1f019f7

Synchronizing local compiler cache.

Browse files
Files changed (9) hide show
  1. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/2596378c026ba9520cff.json +1 -0
  2. neuronxcc-2.16.372.0+4a9b2326/MODULE_20ebc8f6bf90da880b7d+613edded/model.neff +1 -1
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_2e9f2f3a425a7c54a43f+613edded/model.neff +1 -1
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_328290edc16f896de0f3+613edded/model.neff +1 -1
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff +1 -1
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff +1 -1
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff +1 -1
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_97cbcc47f9c08a6a6ba1+613edded/model.neff +1 -1
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff +1 -1
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/2596378c026ba9520cff.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "checkpoint_revision": "74fbf131a939963dd1e244389bb61ad0d0440a4d", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.16.372.0+4a9b2326/MODULE_20ebc8f6bf90da880b7d+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e41e85ad131c3915711d5cb89d86718a102497b315add7fe73ab56699eb2403
3
  size 6042624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d608b98ce144070f5e4e2946fc984369052a1936dde761d20bf542ab3bacc3
3
  size 6042624
neuronxcc-2.16.372.0+4a9b2326/MODULE_2e9f2f3a425a7c54a43f+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0bf925a65d289b96b884d9fe192914f6783a51c6cb5f86eab96b91af290f538
3
  size 29225984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a46f32ba6a4ab96b5704851e1532257c41c21031efe298690860b34c87817cc
3
  size 29225984
neuronxcc-2.16.372.0+4a9b2326/MODULE_328290edc16f896de0f3+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2b5aa96226ad698dc2f0b661311988cca8a196f2cff32d3cd2958c3bf24961d
3
  size 11664384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92838cbc33a798066dd113e804c4cffdd18c13c932b970b889a2b2be09e6330
3
  size 11664384
neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ebf416056af21adc3bc3d71057c68e6353e2f8d7e384b6741366543b8ec0de
3
  size 7803904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55254fa7cc84ed2c53d21177d4593a3d67aee29ac21b8ea690b080b327d622d6
3
  size 7803904
neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e7c98cc9bf2a57760705a932a6f1c62de9f0d31c125e997d8b03d2ae2ad602a
3
  size 5970944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee9cc60f35b7a6d07a396cdb7952d261dfb276e4bf4bab8c5ad41e7ad16b995
3
  size 5970944
neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63dc2a42eb970f65a692123d929236a469a216ceede8b2129df0cd2ccaca26e7
3
  size 6042624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc748b8c1c8ceb28130e853d22d0a845c31944e937435e745a182e268b1c3045
3
  size 6042624
neuronxcc-2.16.372.0+4a9b2326/MODULE_97cbcc47f9c08a6a6ba1+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ec42b4bc330cd04fdf1eeb2458132e57d06eaec28ea5c647896319e743c4b2
3
  size 3103744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07115d49f8c735e2d3a8f5821aed28147cbc94d55ec104474050aa8f1f70b5f0
3
  size 3103744
neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9745b0e63860d8d1c07a88c52d0361b4e9f86c89dd586d94d7a6afd3decfb6d0
3
  size 10415104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82858de1f06a352a9f5c8d36841d5f72d40cfa45be4c8a499ace797c84c2c5f3
3
  size 10415104