Gahow Wang
7cb4cac56d
request_model values like qwen-plus matched no registered family, so resolve_model_family fell through to its "glm5" default and the formatter rendered canonical_prompt with the GLM-5 chat template and tokenized release blocks with the GLM-5 tokenizer. The fallback is silent, so nothing surfaced it. Register the family, ship Qwen3-plus tokenizer/chat_template (the template was embedded in tokenizer_config.json upstream and is extracted here), and add a QwenPlusTraceAdapter ahead of the GLM catch-all in get_raw_adapter -- the registry entry alone is not enough, since the adapter is what picks the template. The shared message/tool normalization is factored out of build_glm5_canonical_prompt so both builders use one copy. Measured against provider-reported usage.input_tokens on a 400-request sample, median tokenized/reported ratio goes 0.9449 -> 1.0000, and unique release block count on a 2190-request sample moves 5886 -> 5701. Note deepseek-v4-flash is still unregistered and still resolves to glm5. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
43 lines
1.1 KiB
JSON
43 lines
1.1 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3MoeForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attn_output_gate": false,
|
|
"bos_token_id": 151643,
|
|
"decoder_sparse_step": 1,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 12288,
|
|
"max_position_embeddings": 35840,
|
|
"max_window_layers": 60,
|
|
"mlp_only_layers": [],
|
|
"model_type": "qwen3_moe",
|
|
"moe_intermediate_size": 1536,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 64,
|
|
"num_experts": 128,
|
|
"num_experts_per_tok": 8,
|
|
"num_hidden_layers": 60,
|
|
"num_key_value_heads": 4,
|
|
"output_router_logits": false,
|
|
"partial_rotary_factor": 1.0,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000,
|
|
"router_aux_loss_coef": 0.001,
|
|
"shared_expert_intermediate_size": 0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.3",
|
|
"use_cache": true,
|
|
"use_gemma_rms_norm": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
}
|