Upload folder using huggingface_hub
Browse files- config.json +31 -0
- model.pt +3 -0
- neuron_config.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6144,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"rms_norm_eps": 1e-06,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 1000000,
|
| 24 |
+
"sliding_window": null,
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.51.3",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:466dee9e5d99bf77cfce6eb0dcfa81550c0b3ca67a1d6d5c928380bb290abb84
|
| 3 |
+
size 4077000963
|
neuron_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 3 |
+
"async_mode": false,
|
| 4 |
+
"attn_kernel_enabled": false,
|
| 5 |
+
"batch_size": 1,
|
| 6 |
+
"capacity_factor": null,
|
| 7 |
+
"cc_pipeline_tiling_factor": 2,
|
| 8 |
+
"checkpoint_id": "Qwen/Qwen3-1.7B",
|
| 9 |
+
"checkpoint_revision": "0060bc56d46589041c1048efd1a397421b1142b5",
|
| 10 |
+
"continuous_batching": false,
|
| 11 |
+
"enable_bucketing": false,
|
| 12 |
+
"ep_degree": 1,
|
| 13 |
+
"flash_decoding_enabled": false,
|
| 14 |
+
"fused_qkv": true,
|
| 15 |
+
"glu_mlp": true,
|
| 16 |
+
"is_chunked_prefill": false,
|
| 17 |
+
"local_ranks_size": 2,
|
| 18 |
+
"logical_nc_config": 1,
|
| 19 |
+
"max_batch_size": 1,
|
| 20 |
+
"max_context_length": 64,
|
| 21 |
+
"max_topk": 256,
|
| 22 |
+
"mlp_kernel_enabled": false,
|
| 23 |
+
"mlp_kernel_fuse_residual_add": false,
|
| 24 |
+
"n_active_tokens": 64,
|
| 25 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
| 26 |
+
"num_cores_per_group": 1,
|
| 27 |
+
"on_device_sampling": true,
|
| 28 |
+
"optimum_neuron_version": "0.2.0",
|
| 29 |
+
"output_logits": false,
|
| 30 |
+
"padding_side": "right",
|
| 31 |
+
"pp_degree": 1,
|
| 32 |
+
"qk_layernorm": false,
|
| 33 |
+
"qkv_kernel_enabled": false,
|
| 34 |
+
"rpl_reduce_dtype": "bfloat16",
|
| 35 |
+
"sequence_length": 64,
|
| 36 |
+
"sequence_parallel_enabled": false,
|
| 37 |
+
"speculation_length": 0,
|
| 38 |
+
"start_rank_id": 0,
|
| 39 |
+
"target": null,
|
| 40 |
+
"torch_dtype": "bfloat16",
|
| 41 |
+
"tp_degree": 2,
|
| 42 |
+
"vocab_parallel": false
|
| 43 |
+
}
|