{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"actions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"go_to",
"pick_up_item",
"drop_item"
]
}
},
"required": [
"action"
],
"oneOf": [
{
"properties": {
"action": {
"const": "go_to"
},
"location": {
"type": "string",
"enum": [
"mall",
"backyard"
]
}
},
"required": [
"location"
]
},
{
"properties": {
"action": {
"const": "lay_down"
},
"data": {
"type": "string",
"enum": [
"None"
]
}
},
"required": [
"data"
]
},
{
"properties": {
"action": {
"const": "pick_up_item"
},
"item": {
"type": "string",
"enum": [
"vase",
"coke",
"cake"
]
}
},
"required": [
"item"
]
},
{
"properties": {
"action": {
"const": "drop_item"
},
"item": {
"type": "string",
"enum": [
"vase",
"coke",
"cake"
]
}
},
"required": [
"item"
]
}
]
}
}
},
"required": [
"actions"
]
}
llama cpp server or llama cpp doesn't respect the JSON schema requiring an action parameter
more over there are a few more instances of this when you try for a longer schema that I can show that it seems to be not the model failing but the json schema
{"tid":"13408","timestamp":1717371771,"level":"INFO","function":"main","line":2918,"msg":"build info","build":2793,"commit":"8f8acc86"}
win_llamaserver\server.exe -m models/Meta-Llama-3-8B-Instruct-abliterated-v3_q6.gguf -ngl 9999 --ctx-size 8192 --parallel 4 --override-kv tokenizer.ggml.pre=str:llama3 -fa
{"tid":"13408","timestamp":1717371771,"level":"INFO","function":"main","line":2918,"msg":"build info","build":2793,"commit":"8f8acc86"}
{"tid":"13408","timestamp":1717371771,"level":"INFO","function":"main","line":2925,"msg":"system info","n_threads":12,"n_threads_batch":-1,"total_threads":24,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | "}
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from models/Meta-Llama-3-8B-Instruct-abliterated-v3_q6.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct-abliterated-v3
llama_model_loader: - kv 2: llama.block_count u32 = 32
llama_model_loader: - kv 3: llama.context_length u32 = 8192
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 18
llama_model_loader: - kv 11: llama.vocab_size u32 = 128256
llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["─á ─á", "─á ─á─á─á", "─á─á ─á─á", "...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128001
llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q6_K: 226 tensors
validate_override: Using metadata override ( str) 'tokenizer.ggml.pre' = llama3
llm_load_vocab: special tokens definition check successful ( 256/128256 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 8192
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 8B
llm_load_print_meta: model ftype = Q6_K
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 6.14 GiB (6.56 BPW)
llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct-abliterated-v3
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128001 '<|end_of_text|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
llm_load_tensors: ggml ctx size = 0.30 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: CPU buffer size = 410.98 MiB
llm_load_tensors: CUDA0 buffer size = 5871.99 MiB
.........................................................................................
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 1
llama_new_context_with_model: freq_base = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 1024.00 MiB
llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 2.45 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 258.50 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 24.01 MiB
llama_new_context_with_model: graph nodes = 903
llama_new_context_with_model: graph splits = 2
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"init","line":708,"msg":"initializing slots","n_slots":4}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"init","line":720,"msg":"new slot","id_slot":0,"n_ctx_slot":2048}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"init","line":720,"msg":"new slot","id_slot":1,"n_ctx_slot":2048}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"init","line":720,"msg":"new slot","id_slot":2,"n_ctx_slot":2048}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"init","line":720,"msg":"new slot","id_slot":3,"n_ctx_slot":2048}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"main","line":3015,"msg":"model loaded"}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"main","line":3040,"msg":"chat template","chat_example":"<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHi there<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHow are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n","built_in":true}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"main","line":3768,"msg":"HTTP server listening","hostname":"127.0.0.1","port":"8080","n_threads_http":"23"}
{"tid":"13408","timestamp":1717371775,"level":"INFO","function":"update_slots","line":1807,"msg":"all slots are idle"}
{"tid":"13408","timestamp":1717371778,"level":"INFO","function":"launch_slot_with_task","line":1039,"msg":"slot is processing task","id_slot":3,"id_task":0}
{"tid":"13408","timestamp":1717371778,"level":"INFO","function":"update_slots","line":2091,"msg":"kv cache rm [p0, end)","id_slot":3,"id_task":0,"p0":0}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"print_timings","line":320,"msg":"prompt eval time = 1379.95 ms / 89 tokens ( 15.51 ms per token, 64.50 tokens per second)","id_slot":3,"id_task":0,"t_prompt_processing":1379.95,"n_prompt_tokens_processed":89,"t_token":15.50505617977528,"n_tokens_second":64.49509040182615}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"print_timings","line":336,"msg":"generation eval time = 6566.83 ms / 68 runs ( 96.57 ms per token, 10.36 tokens per second)","id_slot":3,"id_task":0,"t_token_generation":6566.826,"n_decoded":68,"t_token":96.5709705882353,"n_tokens_second":10.355078694029658}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"print_timings","line":346,"msg":" total time = 7946.78 ms","id_slot":3,"id_task":0,"t_prompt_processing":1379.95,"t_token_generation":6566.826,"t_total":7946.776}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"update_slots","line":1789,"msg":"slot released","id_slot":3,"id_task":0,"n_ctx":8192,"n_past":156,"n_system_tokens":0,"n_cache_tokens":156,"truncated":false}
{"tid":"31532","timestamp":1717371786,"level":"INFO","function":"log_server_request","line":2869,"msg":"request","remote_addr":"127.0.0.1","remote_port":60337,"status":200,"method":"POST","path":"/completion","params":{}}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"update_slots","line":1807,"msg":"all slots are idle"}
{"tid":"13408","timestamp":1717371786,"level":"INFO","function":"update_slots","line":1807,"msg":"all slots are idle"}
What happened?
Given this JSON Schema
output:
{"actions": [ {"location":"mall"}, {"item":"cake", "action":"pick_up_item"}, {"item":"cake", "action":"drop_item"} , {"item":"coke", "action":"pick_up_item"}, {"item":"coke", "action":"drop_item"} ] }llama cpp server or llama cpp doesn't respect the JSON schema requiring an action parameter
more over there are a few more instances of this when you try for a longer schema that I can show that it seems to be not the model failing but the json schema
Name and Version
{"tid":"13408","timestamp":1717371771,"level":"INFO","function":"main","line":2918,"msg":"build info","build":2793,"commit":"8f8acc86"}
What operating system are you seeing the problem on?
Windows
Relevant log output