llama.clj
A wrapper for llama.cpp.
Namespaces
com.phronemophobic.llama.raw
Public variables and functions:
- *num-threads*
- api
- cleaner
- ggml_abs
- ggml_abs_inplace
- ggml_acc
- ggml_acc_inplace
- ggml_add
- ggml_add1
- ggml_add1_inplace
- ggml_add_inplace
- ggml_alibi
- ggml_argmax
- GGML_BACKEND_CPU
- GGML_BACKEND_GPU
- GGML_BACKEND_GPU_SPLIT
- ggml_blck_size
- ggml_build_backward
- ggml_build_forward
- ggml_build_forward_ctx
- ggml_build_forward_expand
- ggml_clamp
- ggml_cont
- ggml_cont_inplace
- ggml_conv_1d
- ggml_conv_1d_ph
- ggml_conv_2d
- ggml_cpu_has_arm_fma
- ggml_cpu_has_avx
- ggml_cpu_has_avx2
- ggml_cpu_has_avx512
- ggml_cpu_has_avx512_vbmi
- ggml_cpu_has_avx512_vnni
- ggml_cpu_has_blas
- ggml_cpu_has_clblast
- ggml_cpu_has_cublas
- ggml_cpu_has_f16c
- ggml_cpu_has_fma
- ggml_cpu_has_fp16_va
- ggml_cpu_has_gpublas
- ggml_cpu_has_neon
- ggml_cpu_has_sse3
- ggml_cpu_has_vsx
- ggml_cpu_has_wasm_simd
- ggml_cpy
- ggml_cpy_inplace
- ggml_cross_entropy_loss
- ggml_cross_entropy_loss_back
- ggml_cycles
- ggml_cycles_per_ms
- ggml_diag
- ggml_diag_mask_inf
- ggml_diag_mask_inf_inplace
- ggml_diag_mask_zero
- ggml_diag_mask_zero_inplace
- ggml_div
- ggml_div_inplace
- ggml_dup
- ggml_dup_inplace
- ggml_dup_tensor
- ggml_element_size
- ggml_elu
- ggml_elu_inplace
- ggml_flash_attn
- ggml_flash_attn_back
- ggml_flash_ff
- ggml_format_name
- ggml_fp16_to_fp32
- ggml_fp16_to_fp32_row
- ggml_fp32_to_fp16
- ggml_fp32_to_fp16_row
- ggml_free
- GGML_FTYPE_ALL_F32
- GGML_FTYPE_MOSTLY_F16
- GGML_FTYPE_MOSTLY_Q2_K
- GGML_FTYPE_MOSTLY_Q3_K
- GGML_FTYPE_MOSTLY_Q4_0
- GGML_FTYPE_MOSTLY_Q4_1
- GGML_FTYPE_MOSTLY_Q4_1_SOME_F16
- GGML_FTYPE_MOSTLY_Q4_K
- GGML_FTYPE_MOSTLY_Q5_0
- GGML_FTYPE_MOSTLY_Q5_1
- GGML_FTYPE_MOSTLY_Q5_K
- GGML_FTYPE_MOSTLY_Q6_K
- GGML_FTYPE_MOSTLY_Q8_0
- ggml_ftype_to_ggml_type
- GGML_FTYPE_UNKNOWN
- ggml_gelu
- ggml_gelu_inplace
- ggml_gelu_quick
- ggml_gelu_quick_inplace
- ggml_get_data
- ggml_get_data_f32
- ggml_get_f32_1d
- ggml_get_i32_1d
- ggml_get_max_tensor_size
- ggml_get_mem_buffer
- ggml_get_mem_size
- ggml_get_name
- ggml_get_no_alloc
- ggml_get_rows
- ggml_get_rows_back
- ggml_get_tensor
- ggml_get_unary_op
- ggml_graph_compute
- ggml_graph_compute_with_ctx
- ggml_graph_dump_dot
- ggml_graph_export
- ggml_graph_get_tensor
- ggml_graph_import
- ggml_graph_overhead
- ggml_graph_plan
- ggml_graph_print
- ggml_graph_reset
- ggml_init
- ggml_internal_get_type_traits
- ggml_is_contiguous
- ggml_is_numa
- ggml_is_permuted
- ggml_is_quantized
- ggml_is_transposed
- GGML_LINESEARCH_BACKTRACKING_ARMIJO
- GGML_LINESEARCH_BACKTRACKING_STRONG_WOLFE
- GGML_LINESEARCH_BACKTRACKING_WOLFE
- GGML_LINESEARCH_DEFAULT
- GGML_LINESEARCH_FAIL
- GGML_LINESEARCH_INVALID_PARAMETERS
- GGML_LINESEARCH_MAXIMUM_ITERATIONS
- GGML_LINESEARCH_MAXIMUM_STEP
- GGML_LINESEARCH_MINIMUM_STEP
- ggml_log
- ggml_log_inplace
- ggml_map_binary_f32
- ggml_map_binary_inplace_f32
- ggml_map_custom1_f32
- ggml_map_custom1_inplace_f32
- ggml_map_custom2_f32
- ggml_map_custom2_inplace_f32
- ggml_map_custom3_f32
- ggml_map_custom3_inplace_f32
- ggml_map_unary_f32
- ggml_map_unary_inplace_f32
- ggml_mean
- ggml_mul
- ggml_mul_inplace
- ggml_mul_mat
- ggml_nbytes
- ggml_nbytes_split
- ggml_neg
- ggml_neg_inplace
- ggml_nelements
- ggml_new_f32
- ggml_new_graph
- ggml_new_i32
- ggml_new_tensor
- ggml_new_tensor_1d
- ggml_new_tensor_2d
- ggml_new_tensor_3d
- ggml_new_tensor_4d
- ggml_norm
- ggml_norm_inplace
- ggml_nrows
- ggml_numa_init
- GGML_OBJECT_GRAPH
- GGML_OBJECT_TENSOR
- GGML_OBJECT_WORK_BUFFER
- GGML_OP_ACC
- GGML_OP_ADD
- GGML_OP_ADD1
- GGML_OP_ALIBI
- GGML_OP_ARGMAX
- GGML_OP_CLAMP
- GGML_OP_CONT
- GGML_OP_CONV_1D
- GGML_OP_CONV_2D
- GGML_OP_COUNT
- GGML_OP_CPY
- GGML_OP_CROSS_ENTROPY_LOSS
- GGML_OP_CROSS_ENTROPY_LOSS_BACK
- GGML_OP_DIAG
- GGML_OP_DIAG_MASK_INF
- GGML_OP_DIAG_MASK_ZERO
- GGML_OP_DIV
- GGML_OP_DUP
- GGML_OP_FLASH_ATTN
- GGML_OP_FLASH_ATTN_BACK
- GGML_OP_FLASH_FF
- GGML_OP_GET_ROWS
- GGML_OP_GET_ROWS_BACK
- GGML_OP_LOG
- GGML_OP_MAP_BINARY
- GGML_OP_MAP_CUSTOM1
- GGML_OP_MAP_CUSTOM2
- GGML_OP_MAP_CUSTOM3
- GGML_OP_MAP_UNARY
- GGML_OP_MEAN
- GGML_OP_MUL
- GGML_OP_MUL_MAT
- ggml_op_name
- GGML_OP_NONE
- GGML_OP_NORM
- GGML_OP_OUT_PROD
- GGML_OP_PERMUTE
- GGML_OP_POOL_1D
- GGML_OP_POOL_2D
- GGML_OP_POOL_AVG
- GGML_OP_POOL_COUNT
- GGML_OP_POOL_MAX
- GGML_OP_REPEAT
- GGML_OP_REPEAT_BACK
- GGML_OP_RESHAPE
- GGML_OP_RMS_NORM
- GGML_OP_RMS_NORM_BACK
- GGML_OP_ROPE
- GGML_OP_ROPE_BACK
- GGML_OP_SCALE
- GGML_OP_SET
- GGML_OP_SILU_BACK
- GGML_OP_SOFT_MAX
- GGML_OP_SOFT_MAX_BACK
- GGML_OP_SQR
- GGML_OP_SQRT
- GGML_OP_SUB
- GGML_OP_SUM
- GGML_OP_SUM_ROWS
- ggml_op_symbol
- GGML_OP_TRANSPOSE
- GGML_OP_UNARY
- GGML_OP_VIEW
- GGML_OP_WIN_PART
- GGML_OP_WIN_UNPART
- ggml_opt
- GGML_OPT_ADAM
- ggml_opt_default_params
- GGML_OPT_DID_NOT_CONVERGE
- GGML_OPT_FAIL
- ggml_opt_init
- GGML_OPT_INVALID_WOLFE
- GGML_OPT_LBFGS
- GGML_OPT_NO_CONTEXT
- GGML_OPT_OK
- ggml_opt_resume
- ggml_opt_resume_g
- ggml_out_prod
- ggml_permute
- ggml_pool_1d
- ggml_pool_2d
- ggml_print_object
- ggml_print_objects
- ggml_quantize_chunk
- ggml_quantize_q4_0
- ggml_quantize_q4_1
- ggml_quantize_q5_0
- ggml_quantize_q5_1
- ggml_quantize_q8_0
- ggml_relu
- ggml_relu_inplace
- ggml_repeat
- ggml_repeat_back
- ggml_reshape
- ggml_reshape_1d
- ggml_reshape_2d
- ggml_reshape_3d
- ggml_reshape_4d
- ggml_rms_norm
- ggml_rms_norm_back
- ggml_rms_norm_inplace
- ggml_rope
- ggml_rope_back
- ggml_rope_custom
- ggml_rope_custom_inplace
- ggml_rope_inplace
- ggml_scale
- ggml_scale_inplace
- ggml_set
- ggml_set_1d
- ggml_set_1d_inplace
- ggml_set_2d
- ggml_set_2d_inplace
- ggml_set_f32
- ggml_set_f32_1d
- ggml_set_i32
- ggml_set_i32_1d
- ggml_set_inplace
- ggml_set_name
- ggml_set_no_alloc
- ggml_set_param
- ggml_set_scratch
- ggml_set_zero
- ggml_sgn
- ggml_sgn_inplace
- ggml_silu
- ggml_silu_back
- ggml_silu_inplace
- ggml_soft_max
- ggml_soft_max_back
- ggml_soft_max_back_inplace
- ggml_soft_max_inplace
- ggml_sqr
- ggml_sqr_inplace
- ggml_sqrt
- ggml_sqrt_inplace
- ggml_step
- ggml_step_inplace
- ggml_sub
- ggml_sub_inplace
- ggml_sum
- ggml_sum_rows
- ggml_tanh
- ggml_tanh_inplace
- GGML_TASK_COMPUTE
- GGML_TASK_FINALIZE
- GGML_TASK_INIT
- ggml_tensor_overhead
- ggml_time_init
- ggml_time_ms
- ggml_time_us
- ggml_transpose
- GGML_TYPE_COUNT
- GGML_TYPE_F16
- GGML_TYPE_F32
- GGML_TYPE_I16
- GGML_TYPE_I32
- GGML_TYPE_I8
- ggml_type_name
- GGML_TYPE_Q2_K
- GGML_TYPE_Q3_K
- GGML_TYPE_Q4_0
- GGML_TYPE_Q4_1
- GGML_TYPE_Q4_K
- GGML_TYPE_Q5_0
- GGML_TYPE_Q5_1
- GGML_TYPE_Q5_K
- GGML_TYPE_Q6_K
- GGML_TYPE_Q8_0
- GGML_TYPE_Q8_1
- GGML_TYPE_Q8_K
- ggml_type_size
- ggml_type_sizef
- ggml_unary
- ggml_unary_inplace
- GGML_UNARY_OP_ABS
- GGML_UNARY_OP_ELU
- GGML_UNARY_OP_GELU
- GGML_UNARY_OP_GELU_QUICK
- GGML_UNARY_OP_NEG
- GGML_UNARY_OP_RELU
- GGML_UNARY_OP_SGN
- GGML_UNARY_OP_SILU
- GGML_UNARY_OP_STEP
- GGML_UNARY_OP_TANH
- ggml_used_mem
- ggml_view_1d
- ggml_view_2d
- ggml_view_3d
- ggml_view_4d
- ggml_view_tensor
- ggml_win_part
- ggml_win_unpart
- import-structs!
- libllama-options
- llama-model
- llama_apply_lora_from_file
- llama_backend_free
- llama_backend_init
- llama_context_default_params
- llama_copy_state_data
- llama_eval
- llama_eval_embd
- llama_eval_export
- llama_free
- llama_free_model
- LLAMA_FTYPE_ALL_F32
- LLAMA_FTYPE_MOSTLY_F16
- LLAMA_FTYPE_MOSTLY_Q2_K
- LLAMA_FTYPE_MOSTLY_Q3_K_L
- LLAMA_FTYPE_MOSTLY_Q3_K_M
- LLAMA_FTYPE_MOSTLY_Q3_K_S
- LLAMA_FTYPE_MOSTLY_Q4_0
- LLAMA_FTYPE_MOSTLY_Q4_1
- LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16
- LLAMA_FTYPE_MOSTLY_Q4_K_M
- LLAMA_FTYPE_MOSTLY_Q4_K_S
- LLAMA_FTYPE_MOSTLY_Q5_0
- LLAMA_FTYPE_MOSTLY_Q5_1
- LLAMA_FTYPE_MOSTLY_Q5_K_M
- LLAMA_FTYPE_MOSTLY_Q5_K_S
- LLAMA_FTYPE_MOSTLY_Q6_K
- LLAMA_FTYPE_MOSTLY_Q8_0
- llama_get_embeddings
- llama_get_kv_cache_token_count
- llama_get_logits
- llama_get_state_size
- llama_get_timings
- llama_get_vocab
- llama_get_vocab_from_model
- llama_grammar_accept_token
- llama_grammar_free
- llama_grammar_init
- LLAMA_GRETYPE_ALT
- LLAMA_GRETYPE_CHAR
- LLAMA_GRETYPE_CHAR_ALT
- LLAMA_GRETYPE_CHAR_NOT
- LLAMA_GRETYPE_CHAR_RNG_UPPER
- LLAMA_GRETYPE_END
- LLAMA_GRETYPE_RULE_REF
- llama_init_from_file
- llama_load_model_from_file
- llama_load_session_file
- llama_max_devices
- llama_mlock_supported
- llama_mmap_supported
- llama_model_apply_lora_from_file
- llama_model_quantize
- llama_model_quantize_default_params
- llama_n_ctx
- llama_n_ctx_from_model
- llama_n_embd
- llama_n_embd_from_model
- llama_n_vocab
- llama_n_vocab_from_model
- llama_new_context_with_model
- llama_print_system_info
- llama_print_timings
- llama_reset_timings
- llama_sample_classifier_free_guidance
- llama_sample_frequency_and_presence_penalties
- llama_sample_grammar
- llama_sample_repetition_penalty
- llama_sample_softmax
- llama_sample_tail_free
- llama_sample_temperature
- llama_sample_token
- llama_sample_token_greedy
- llama_sample_token_mirostat
- llama_sample_token_mirostat_v2
- llama_sample_top_k
- llama_sample_top_p
- llama_sample_typical
- llama_save_session_file
- llama_set_rng_seed
- llama_set_state_data
- llama_time_us
- llama_token_bos
- llama_token_eos
- llama_token_nl
- llama_token_to_str
- llama_token_to_str_with_model
- llama_tokenize
- llama_tokenize_with_model