# ollama serve:

GET /api/version
{"version":"0.24.0"}

GET /api/tags
{"models":[{"name":"gemma-4-26B-A4B-it-UD-Q4_K_M:latest","model":"gemma-4-26B-A4B-it-UD-Q4_K_M:latest","modified_at":"2026-05-15T12:43:43.896860597+02:00","size":16868241115,"digest":"b16ef1d08ff9df45d8d95d352be6b0578785d9ab2d7e2a78a14151292b6093a4","details":{"parent_model":"","format":"gguf","family":"gemma4","families":["gemma4"],"parameter_size":"25.2B","quantization_level":"Q4_K_M"}},{"name":"gemma4-e4b-q4:latest","model":"gemma4-e4b-q4:latest","modified_at":"2026-05-09T17:04:49.482936443+02:00","size":4977169498,"digest":"50ddaa9b8045236a361e88c886904c9b6486fafd3434411fc897dc0e278f612a","details":{"parent_model":"","format":"gguf","family":"gemma4","families":["gemma4"],"parameter_size":"7.5B","quantization_level":"Q4_K_M"}}]}

POST /api/show
request: {"model": "gemma-4-26B-A4B-it-UD-Q4_K_M:latest"}
response: {"modelfile":"# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this, replace FROM with:\n# FROM gemma-4-26B-A4B-it-UD-Q4_K_M:latest\n\nFROM /home/sb/.ollama/models/blobs/sha256-b8707e57f676d8dd1b80f623b45200cc92e6966b0e95275e606f412095a49fde\nTEMPLATE {{ .Prompt }}\nRENDERER gemma4\nPARSER gemma4\nPARAMETER stop \u003cturn|\u003e\n","parameters":"stop                           \"\u003cturn|\u003e\"","template":"{{ .Prompt }}","details":{"parent_model":"/home/sb/.ollama/models/blobs/sha256-b8707e57f676d8dd1b80f623b45200cc92e6966b0e95275e606f412095a49fde","format":"gguf","family":"gemma4","families":["gemma4"],"parameter_size":"25.2B","quantization_level":"Q4_K_M"},"model_info":{"gemma4.attention.head_count":16,"gemma4.attention.head_count_kv":null,"gemma4.attention.key_length":512,"gemma4.attention.key_length_swa":256,"gemma4.attention.layer_norm_rms_epsilon":0.000001,"gemma4.attention.shared_kv_layers":0,"gemma4.attention.sliding_window":1024,"gemma4.attention.sliding_window_pattern":null,"gemma4.attention.value_length":512,"gemma4.attention.value_length_swa":256,"gemma4.block_count":30,"gemma4.context_length":262144,"gemma4.embedding_length":2816,"gemma4.embedding_length_per_layer_input":0,"gemma4.expert_count":128,"gemma4.expert_feed_forward_length":704,"gemma4.expert_used_count":8,"gemma4.feed_forward_length":2112,"gemma4.final_logit_softcapping":30,"gemma4.rope.dimension_count":512,"gemma4.rope.dimension_count_swa":256,"gemma4.rope.freq_base":1000000,"gemma4.rope.freq_base_swa":10000,"general.architecture":"gemma4","general.base_model.0.name":"Gemma 4 26B A4B It","general.base_model.0.organization":"Google","general.base_model.0.repo_url":"https://huggingface.co/google/gemma-4-26B-A4B-it","general.base_model.count":1,"general.basename":"Gemma-4-26B-A4B-It","general.file_type":15,"general.finetune":"it","general.license":"apache-2.0","general.license.link":"https://ai.google.dev/gemma/docs/gemma_4_license","general.parameter_count":25233142046,"general.quantization_version":2,"general.quantized_by":"Unsloth","general.repo_url":"https://huggingface.co/unsloth","general.sampling.temp":1,"general.sampling.top_k":64,"general.sampling.top_p":0.95,"general.size_label":"26B-A4B","general.tags":null,"general.type":"model","quantize.imatrix.chunks_count":141,"quantize.imatrix.dataset":"unsloth_calibration_gemma-4-26B-A4B-it.txt","quantize.imatrix.entries_count":295,"quantize.imatrix.file":"gemma-4-26B-A4B-it-GGUF/imatrix_unsloth.gguf","tokenizer.ggml.add_bos_token":true,"tokenizer.ggml.add_space_prefix":false,"tokenizer.ggml.bos_token_id":2,"tokenizer.ggml.eos_token_id":106,"tokenizer.ggml.mask_token_id":4,"tokenizer.ggml.merges":null,"tokenizer.ggml.model":"gemma4","tokenizer.ggml.padding_token_id":0,"tokenizer.ggml.scores":null,"tokenizer.ggml.token_type":null,"tokenizer.ggml.tokens":null,"tokenizer.ggml.unknown_token_id":3},"tensors":[{"name":"output_norm.weight","type":"F32","shape":[2816]},{"name":"rope_freqs.weight","type":"F32","shape":[256]},{"name":"token_embd.weight","type":"Q8_0","shape":[2816,262144]},{"name":"blk.0.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.0.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.0.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.0.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.0.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.0.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.0.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.0.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.0.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.0.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.0.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.0.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.0.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.0.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.0.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.0.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.0.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.0.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.0.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.0.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.0.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.0.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.1.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.1.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.1.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.1.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.1.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.1.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.1.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.1.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.1.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.1.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.1.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.1.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.1.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.1.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.1.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.1.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.1.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.1.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.1.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.1.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.1.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.1.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.2.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.2.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.2.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.2.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.2.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.2.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.2.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.2.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.2.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.2.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.2.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.2.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.2.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.2.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.2.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.2.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.2.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.2.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.2.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.2.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.2.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.2.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.3.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.3.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.3.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.3.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.3.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.3.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.3.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.3.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.3.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.3.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.3.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.3.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.3.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.3.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.3.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.3.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.3.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.3.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.3.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.3.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.3.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.3.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.4.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.4.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.4.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.4.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.4.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.4.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.4.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.4.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.4.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.4.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.4.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.4.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.4.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.4.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.4.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.4.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.4.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.4.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.4.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.4.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.4.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.4.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.5.attn_k.weight","type":"Q8_0","shape":[2816,1024]},{"name":"blk.5.attn_k_norm.weight","type":"F32","shape":[512]},{"name":"blk.5.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.5.attn_output.weight","type":"Q8_0","shape":[8192,2816]},{"name":"blk.5.attn_q.weight","type":"Q8_0","shape":[2816,8192]},{"name":"blk.5.attn_q_norm.weight","type":"F32","shape":[512]},{"name":"blk.5.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.5.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.5.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.5.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.5.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.5.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.5.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.5.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.5.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.5.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.5.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.5.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.5.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.5.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.5.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.6.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.6.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.6.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.6.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.6.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.6.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.6.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.6.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.6.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.6.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.6.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.6.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.6.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.6.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.6.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.6.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.6.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.6.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.6.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.6.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.6.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.6.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.7.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.7.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.7.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.7.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.7.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.7.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.7.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.7.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.7.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.7.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.7.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.7.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.7.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.7.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.7.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.7.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.7.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.7.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.7.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.7.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.7.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.7.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.8.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.8.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.8.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.8.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.8.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.8.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.8.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.8.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.8.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.8.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.8.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.8.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.8.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.8.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.8.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.8.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.8.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.8.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.8.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.8.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.8.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.8.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.9.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.9.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.9.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.9.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.9.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.9.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.9.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.9.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.9.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.9.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.9.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.9.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.9.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.9.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.9.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.9.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.9.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.9.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.9.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.9.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.9.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.9.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.10.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.10.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.10.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.10.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.10.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.10.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.10.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.10.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.10.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.10.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.10.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.10.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.10.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.10.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.10.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.10.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.10.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.10.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.10.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.10.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.10.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.10.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.11.attn_k.weight","type":"Q8_0","shape":[2816,1024]},{"name":"blk.11.attn_k_norm.weight","type":"F32","shape":[512]},{"name":"blk.11.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.11.attn_output.weight","type":"Q8_0","shape":[8192,2816]},{"name":"blk.11.attn_q.weight","type":"Q8_0","shape":[2816,8192]},{"name":"blk.11.attn_q_norm.weight","type":"F32","shape":[512]},{"name":"blk.11.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.11.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.11.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.11.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.11.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.11.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.11.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.11.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.11.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.11.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.11.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.11.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.11.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.11.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.11.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.12.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.12.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.12.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.12.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.12.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.12.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.12.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.12.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.12.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.12.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.12.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.12.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.12.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.12.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.12.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.12.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.12.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.12.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.12.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.12.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.12.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.12.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.13.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.13.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.13.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.13.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.13.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.13.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.13.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.13.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.13.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.13.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.13.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.13.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.13.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.13.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.13.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.13.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.13.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.13.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.13.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.13.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.13.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.13.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.14.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.14.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.14.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.14.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.14.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.14.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.14.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.14.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.14.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.14.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.14.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.14.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.14.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.14.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.14.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.14.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.14.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.14.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.14.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.14.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.14.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.14.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.15.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.15.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.15.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.15.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.15.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.15.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.15.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.15.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.15.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.15.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.15.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.15.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.15.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.15.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.15.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.15.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.15.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.15.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.15.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.15.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.15.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.15.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.16.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.16.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.16.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.16.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.16.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.16.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.16.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.16.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.16.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.16.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.16.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.16.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.16.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.16.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.16.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.16.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.16.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.16.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.16.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.16.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.16.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.16.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.17.attn_k.weight","type":"Q8_0","shape":[2816,1024]},{"name":"blk.17.attn_k_norm.weight","type":"F32","shape":[512]},{"name":"blk.17.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.17.attn_output.weight","type":"Q8_0","shape":[8192,2816]},{"name":"blk.17.attn_q.weight","type":"Q8_0","shape":[2816,8192]},{"name":"blk.17.attn_q_norm.weight","type":"F32","shape":[512]},{"name":"blk.17.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.17.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.17.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.17.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.17.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.17.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.17.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.17.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.17.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.17.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.17.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.17.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.17.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.17.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.17.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.18.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.18.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.18.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.18.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.18.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.18.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.18.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.18.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.18.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.18.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.18.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.18.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.18.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.18.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.18.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.18.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.18.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.18.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.18.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.18.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.18.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.18.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.19.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.19.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.19.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.19.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.19.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.19.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.19.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.19.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.19.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.19.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.19.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.19.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.19.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.19.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.19.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.19.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.19.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.19.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.19.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.19.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.19.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.19.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.20.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.20.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.20.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.20.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.20.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.20.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.20.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.20.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.20.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.20.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.20.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.20.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.20.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.20.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.20.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.20.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.20.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.20.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.20.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.20.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.20.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.20.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.21.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.21.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.21.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.21.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.21.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.21.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.21.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.21.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.21.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.21.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.21.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.21.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.21.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.21.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.21.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.21.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.21.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.21.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.21.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.21.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.21.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.21.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.22.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.22.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.22.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.22.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.22.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.22.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.22.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.22.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.22.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.22.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.22.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.22.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.22.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.22.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.22.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.22.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.22.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.22.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.22.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.22.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.22.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.22.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.23.attn_k.weight","type":"Q8_0","shape":[2816,1024]},{"name":"blk.23.attn_k_norm.weight","type":"F32","shape":[512]},{"name":"blk.23.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.23.attn_output.weight","type":"Q8_0","shape":[8192,2816]},{"name":"blk.23.attn_q.weight","type":"Q8_0","shape":[2816,8192]},{"name":"blk.23.attn_q_norm.weight","type":"F32","shape":[512]},{"name":"blk.23.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.23.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.23.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.23.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.23.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.23.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.23.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.23.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.23.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.23.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.23.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.23.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.23.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.23.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.23.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.24.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.24.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.24.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.24.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.24.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.24.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.24.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.24.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.24.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.24.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.24.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.24.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.24.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.24.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.24.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.24.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.24.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.24.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.24.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.24.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.24.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.24.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.25.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.25.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.25.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.25.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.25.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.25.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.25.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.25.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.25.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.25.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.25.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.25.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.25.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.25.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.25.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.25.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.25.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.25.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.25.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.25.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.25.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.25.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.26.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.26.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.26.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.26.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.26.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.26.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.26.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.26.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.26.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.26.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.26.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.26.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.26.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.26.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.26.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.26.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.26.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.26.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.26.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.26.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.26.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.26.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.27.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.27.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.27.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.27.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.27.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.27.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.27.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.27.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.27.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.27.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.27.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.27.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.27.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.27.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.27.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.27.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.27.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.27.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.27.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.27.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.27.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.27.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.28.attn_k.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.28.attn_k_norm.weight","type":"F32","shape":[256]},{"name":"blk.28.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.28.attn_output.weight","type":"Q8_0","shape":[4096,2816]},{"name":"blk.28.attn_q.weight","type":"Q8_0","shape":[2816,4096]},{"name":"blk.28.attn_q_norm.weight","type":"F32","shape":[256]},{"name":"blk.28.attn_v.weight","type":"Q8_0","shape":[2816,2048]},{"name":"blk.28.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.28.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.28.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.28.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.28.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.28.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.28.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.28.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.28.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.28.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.28.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.28.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.28.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.28.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.28.pre_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.29.attn_k.weight","type":"Q8_0","shape":[2816,1024]},{"name":"blk.29.attn_k_norm.weight","type":"F32","shape":[512]},{"name":"blk.29.attn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.29.attn_output.weight","type":"Q8_0","shape":[8192,2816]},{"name":"blk.29.attn_q.weight","type":"Q8_0","shape":[2816,8192]},{"name":"blk.29.attn_q_norm.weight","type":"F32","shape":[512]},{"name":"blk.29.ffn_down.weight","type":"Q8_0","shape":[2112,2816]},{"name":"blk.29.ffn_down_exps.scale","type":"F32","shape":[128]},{"name":"blk.29.ffn_down_exps.weight","type":"Q5_1","shape":[704,2816,128]},{"name":"blk.29.ffn_gate.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.29.ffn_gate_inp.scale","type":"F32","shape":[2816]},{"name":"blk.29.ffn_gate_inp.weight","type":"F32","shape":[2816,128]},{"name":"blk.29.ffn_gate_up_exps.weight","type":"Q4_K","shape":[2816,1408,128]},{"name":"blk.29.ffn_norm.weight","type":"F32","shape":[2816]},{"name":"blk.29.ffn_up.weight","type":"Q8_0","shape":[2816,2112]},{"name":"blk.29.layer_output_scale.weight","type":"F32","shape":[1]},{"name":"blk.29.post_attention_norm.weight","type":"F32","shape":[2816]},{"name":"blk.29.post_ffw_norm.weight","type":"F32","shape":[2816]},{"name":"blk.29.post_ffw_norm_1.weight","type":"F32","shape":[2816]},{"name":"blk.29.post_ffw_norm_2.weight","type":"F32","shape":[2816]},{"name":"blk.29.pre_ffw_norm_2.weight","type":"F32","shape":[2816]}],"capabilities":["completion","tools","thinking"],"modified_at":"2026-05-15T12:43:43.896860597+02:00"}

# llama-server

GET /props
{"default_generation_settings":{"params":{"seed":4294967295,"temperature":1.0,"dynatemp_range":0.0,"dynatemp_exponent":1.0,"top_k":64,"top_p":0.949999988079071,"min_p":0.05000000074505806,"top_n_sigma":-1.0,"xtc_probability":0.0,"xtc_threshold":0.10000000149011612,"typical_p":1.0,"repeat_last_n":64,"repeat_penalty":1.0,"presence_penalty":0.0,"frequency_penalty":0.0,"dry_multiplier":0.0,"dry_base":1.75,"dry_allowed_length":2,"dry_penalty_last_n":-1,"mirostat":0,"mirostat_tau":5.0,"mirostat_eta":0.10000000149011612,"max_tokens":-1,"n_predict":-1,"n_keep":0,"n_discard":0,"ignore_eos":false,"stream":true,"n_probs":0,"min_keep":0,"chat_format":"Content-only","reasoning_format":"none","reasoning_in_content":false,"generation_prompt":"","samplers":["penalties","dry","top_n_sigma","top_k","typ_p","top_p","min_p","xtc","temperature"],"speculative.types":"none","timings_per_token":false,"post_sampling_probs":false,"backend_sampling":false,"lora":[]},"n_ctx":16128},"total_slots":4,"model_alias":"gemma-4-E4B-it-Q6_K.gguf","model_path":"/mnt/data/data/lm/models/gguf/s/gemma-4-E4B-it-Q6_K.gguf","modalities":{"vision":false,"audio":false},"media_marker":"<__media_h6cQgpf6gHGxot8QO2lPIcHvCadr4XSS__>","endpoint_slots":true,"endpoint_props":false,"endpoint_metrics":false,"webui":true,"webui_settings":{},"chat_template":"{%- macro format_parameters(properties, required) -%}\n    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n    {%- set ns = namespace(found_first=false) -%}\n    {%- for key, value in properties | dictsort -%}\n        {%- set add_comma = false -%}\n        {%- if key not in standard_keys -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {{ key }}:{\n            {%- if value['description'] -%}\n                description:<|\"|>{{ value['description'] }}<|\"|>\n                {%- set add_comma = true -%}\n            {%- endif -%}\n            {%- if value['type'] | upper == 'STRING' -%}\n                {%- if value['enum'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    enum:{{ format_argument(value['enum']) }}\n                {%- endif -%}\n            {%- elif value['type'] | upper == 'ARRAY' -%}\n                {%- if value['items'] is mapping and value['items'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    items:{\n                    {%- set ns_items = namespace(found_first=false) -%}\n                    {%- for item_key, item_value in value['items'] | dictsort -%}\n                        {%- if item_value is not none -%}\n                            {%- if ns_items.found_first %},{% endif -%}\n                            {%- set ns_items.found_first = true -%}\n                            {%- if item_key == 'properties' -%}\n                                properties:{\n                                {%- if item_value is mapping -%}\n                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n                                {%- endif -%}\n                                }\n                            {%- elif item_key == 'required' -%}\n                                required:[\n                                {%- for req_item in item_value -%}\n                                    <|\"|>{{- req_item -}}<|\"|>\n                                    {%- if not loop.last %},{% endif -%}\n                                {%- endfor -%}\n                                ]\n                            {%- elif item_key == 'type' -%}\n                                {%- if item_value is string -%}\n                                    type:{{ format_argument(item_value | upper) }}\n                                {%- else -%}\n                                    type:{{ format_argument(item_value | map('upper') | list) }}\n                                {%- endif -%}\n                            {%- else -%}\n                                {{ item_key }}:{{ format_argument(item_value) }}\n                            {%- endif -%}\n                        {%- endif -%}\n                    {%- endfor -%}\n                    }\n                {%- endif -%}\n            {%- endif -%}\n            {%- if value['nullable'] %}\n                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                nullable:true\n            {%- endif -%}\n            {%- if value['type'] | upper == 'OBJECT' -%}\n                {%- if value['properties'] is defined and value['properties'] is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n                    }\n                {%- elif value is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value, value['required'] | default([])) -}}\n                    }\n                {%- endif -%}\n                {%- if value['required'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    required:[\n                    {%- for item in value['required'] | default([]) -%}\n                        <|\"|>{{- item -}}<|\"|>\n                        {%- if not loop.last %},{% endif -%}\n                    {%- endfor -%}\n                    ]\n                {%- endif -%}\n            {%- endif -%}\n            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n            type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n        {%- endif -%}\n    {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n    declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n    {%- set params = tool_data['function']['parameters'] -%}\n    {%- if params -%}\n        ,parameters:{\n        {%- if params['properties'] -%}\n            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n        {%- endif -%}\n        {%- if params['required'] -%}\n            required:[\n            {%- for item in params['required'] -%}\n                <|\"|>{{- item -}}<|\"|>\n                {{- ',' if not loop.last -}}\n            {%- endfor -%}\n            ],\n        {%- endif -%}\n        {%- if params['type'] -%}\n            type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if 'response' in tool_data['function'] -%}\n        {%- set response_declaration = tool_data['function']['response'] -%}\n        ,response:{\n        {%- if response_declaration['description'] -%}\n            description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n        {%- endif -%}\n        {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n            type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n    {%- if argument is string -%}\n        {{- '<|\"|>' + argument + '<|\"|>' -}}\n    {%- elif argument is boolean -%}\n        {{- 'true' if argument else 'false' -}}\n    {%- elif argument is mapping -%}\n        {{- '{' -}}\n        {%- set ns = namespace(found_first=false) -%}\n        {%- for key, value in argument | dictsort -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {%- if escape_keys -%}\n                {{- '<|\"|>' + key + '<|\"|>' -}}\n            {%- else -%}\n                {{- key -}}\n            {%- endif -%}\n            :{{- format_argument(value, escape_keys=escape_keys) -}}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- elif argument is sequence -%}\n        {{- '[' -}}\n        {%- for item in argument -%}\n            {{- format_argument(item, escape_keys=escape_keys) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- ']' -}}\n    {%- else -%}\n        {{- argument -}}\n    {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n    {%- set ns = namespace(result='') -%}\n    {%- for part in text.split('<channel|>') -%}\n        {%- if '<|channel>' in part -%}\n            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n        {%- else -%}\n            {%- set ns.result = ns.result + part -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n    {{- '<|tool_response>' -}}\n    {%- if response is mapping -%}\n        {{- 'response:' + tool_name + '{' -}}\n        {%- for key, value in response | dictsort -%}\n            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- else -%}\n        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n    {%- endif -%}\n    {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n    {{- '<|turn>system\\n' -}}\n\n    {#- Inject Thinking token at the very top of the FIRST system turn -#}\n    {%- if enable_thinking is defined and enable_thinking -%}\n        {{- '<|think|>\\n' -}}\n        {%- set ns.prev_message_type = 'think' -%}\n    {%- endif -%}\n\n    {%- if messages[0]['role'] in ['system', 'developer'] -%}\n        {{- messages[0]['content'] | trim -}}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\n\n    {%- if tools -%}\n        {%- for tool in tools %}\n            {{- '<|tool>' -}}\n            {{- format_function_declaration(tool) | trim -}}\n            {{- '<tool|>' -}}\n        {%- endfor %}\n        {%- set ns.prev_message_type = 'tool' -%}\n    {%- endif -%}\n\n    {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n    {%- if loop_messages[i]['role'] == 'user' -%}\n        {%- set ns_turn.last_user_idx = i -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n    {%- if message['role'] != 'tool' -%}\n    {%- set ns.prev_message_type = None -%}\n    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n    {%- set prev_nt = namespace(role=None, found=false) -%}\n    {%- if loop.index0 > 0 -%}\n        {%- for j in range(loop.index0 - 1, -1, -1) -%}\n            {%- if not prev_nt.found -%}\n                {%- if loop_messages[j]['role'] != 'tool' -%}\n                    {%- set prev_nt.role = loop_messages[j]['role'] -%}\n                    {%- set prev_nt.found = true -%}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- endif -%}\n    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n    {%- if not continue_same_model_turn -%}\n        {{- '<|turn>' + role + '\\n' }}\n    {%- endif -%}\n\n    {#- Render reasoning/reasoning_content as thinking channel -#}\n    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n        {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n    {%- endif -%}\n\n            {%- if message['tool_calls'] -%}\n                {%- for tool_call in message['tool_calls'] -%}\n                    {%- set function = tool_call['function'] -%}\n                    {{- '<|tool_call>call:' + function['name'] + '{' -}}\n                    {%- if function['arguments'] is mapping -%}\n                        {%- set ns_args = namespace(found_first=false) -%}\n                        {%- for key, value in function['arguments'] | dictsort -%}\n                            {%- if ns_args.found_first %},{% endif -%}\n                            {%- set ns_args.found_first = true -%}\n                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n                        {%- endfor -%}\n                    {%- elif function['arguments'] is string -%}\n                        {{- function['arguments'] -}}\n                    {%- endif -%}\n                    {{- '}<tool_call|>' -}}\n                {%- endfor -%}\n                {%- set ns.prev_message_type = 'tool_call' -%}\n            {%- endif -%}\n\n            {%- set ns_tr_out = namespace(flag=false) -%}\n            {%- if message.get('tool_responses') -%}\n                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n                {%- for tool_response in message['tool_responses'] -%}\n                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n                    {%- set ns_tr_out.flag = true -%}\n                    {%- set ns.prev_message_type = 'tool_response' -%}\n                {%- endfor -%}\n            {%- elif message.get('tool_calls') -%}\n                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n                {%- set ns_tool_scan = namespace(stopped=false) -%}\n                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n                    {%- if ns_tool_scan.stopped -%}\n                    {%- elif loop_messages[k]['role'] != 'tool' -%}\n                        {%- set ns_tool_scan.stopped = true -%}\n                    {%- else -%}\n                        {%- set follow = loop_messages[k] -%}\n                        {#- Resolve tool_call_id to function name -#}\n                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n                        {%- for tc in message['tool_calls'] -%}\n                            {%- if tc.get('id') == follow.get('tool_call_id') -%}\n                                {%- set ns_tname.name = tc['function']['name'] -%}\n                            {%- endif -%}\n                        {%- endfor -%}\n                        {#- Handle content as string or content-parts array -#}\n                        {%- set tool_body = follow.get('content') -%}\n                        {%- if tool_body is string -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- elif tool_body is sequence and tool_body is not string -%}\n                            {%- set ns_txt = namespace(s='') -%}\n                            {%- for part in tool_body -%}\n                                {%- if part.get('type') == 'text' -%}\n                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n                                {%- endif -%}\n                            {%- endfor -%}\n                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n                        {%- else -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- endif -%}\n                        {%- set ns_tr_out.flag = true -%}\n                        {%- set ns.prev_message_type = 'tool_response' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n            {%- if message['content'] is string -%}\n                {%- if role == 'model' -%}\n                    {{- strip_thinking(message['content']) -}}\n                {%- else -%}\n                    {{- message['content'] | trim -}}\n                {%- endif -%}\n            {%- elif message['content'] is sequence -%}\n                {%- for item in message['content'] -%}\n                    {%- if item['type'] == 'text' -%}\n                        {%- if role == 'model' -%}\n                            {{- strip_thinking(item['text']) -}}\n                        {%- else -%}\n                            {{- item['text'] | trim -}}\n                        {%- endif -%}\n                    {%- elif item['type'] == 'image' -%}\n                        {{- '<|image|>' -}}\n                        {%- set ns.prev_message_type = 'image' -%}\n                    {%- elif item['type'] == 'audio' -%}\n                        {{- '<|audio|>' -}}\n                        {%- set ns.prev_message_type = 'audio' -%}\n                    {%- elif item['type'] == 'video' -%}\n                        {{- '<|video|>' -}}\n                        {%- set ns.prev_message_type = 'video' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n            {{- '<|tool_response>' -}}\n        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}\n            {{- '<turn|>\\n' -}}\n        {%- endif -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n        {{- '<|turn>model\\n' -}}\n    {%- endif -%}\n{%- endif -%}","chat_template_caps":{"supports_object_arguments":true,"supports_parallel_tool_calls":true,"supports_preserve_reasoning":true,"supports_string_content":true,"supports_system_role":true,"supports_tool_calls":true,"supports_tools":true,"supports_typed_content":false},"bos_token":"<bos>","eos_token":"<turn|>","build_info":"b9164-d5dc2e0a0","is_sleeping":false}

GET /slots
[{"id":0,"n_ctx":16128,"speculative":false,"is_processing":false},{"id":1,"n_ctx":16128,"speculative":false,"is_processing":false},{"id":2,"n_ctx":16128,"speculative":false,"is_processing":false},{"id":3,"n_ctx":16128,"speculative":false,"is_processing":false}]

GET /v1/models
{"models":[{"name":"gemma-4-E4B-it-Q6_K.gguf","model":"gemma-4-E4B-it-Q6_K.gguf","modified_at":"","size":"","digest":"","type":"model","description":"","tags":[""],"capabilities":["completion"],"parameters":"","details":{"parent_model":"","format":"gguf","family":"","families":[""],"parameter_size":"","quantization_level":""}}],"object":"list","data":[{"id":"gemma-4-E4B-it-Q6_K.gguf","aliases":[],"tags":[],"object":"model","created":1778857538,"owned_by":"llamacpp","meta":{"vocab_type":2,"n_vocab":262144,"n_ctx":16128,"n_ctx_train":131072,"n_embd":2560,"n_params":7518069290,"size":7059101864}}]}

