Georgi Gerganov
cf658adc83
llm : add Falcon support (#2717)
* llama : refactor GGUF constants into static maps
* llama : check if model architecture is known
* llama : refactor llama_model_load_internal()
* gguf : add KV constant maps
* llm : read arch-specific KVs
* convert : add dummy scores + types
* falcon : load tensor data (CPU only)
* llama : fix loading progress bar
* llama : add arch member to llama_model
* falcon : CPU inference working
* falcon : support non-40B models
* falcon : minor
* llama : minor updates
ggml-ci
* convert-falcon-hf-to-gguf.py : fix special token mapping
* llama.cpp : llama default UNK token = id 0
* llama.cpp : fix bpe tokenizer
* llama.cpp : fix the fix of bpe tokenizer
* ggml : pass eps to ggml_norm
* metal : implement RoPE (mode = 2) + avoid ggml_repeat
* ggml : ggml_repeat always creates new tensor
* falcon : copy-paste self-attention from LLaMA
* metal : print extra compute pipeline info
* falcon : minor changes (still chasing the Metal problem)
* llama.cpp : fix linefeed token
* metal : fix GELU kernel numerical stability by using precise::tanh
* metal : temporary workaround for the concurrency optimization bug
* falcon : add CUDA offloading (#2739)
* llama : better model naming and size reporting
* llama : prep new tokenizer support
* llama : advanced BPE tokenizer based on ggllm.cpp imlpementation
* llama : remove oboslete comment
ggml-ci
* common : remove obsolete BPE API + disable test-tokenizer-1
* llama : revert BPE special-case in llama_byte_to_token()
* cuda : add TODOs for RoPE NeoX implementation
* llama : default special tokens based on vocab type
* perplexity : add log for start of tokenization
---------
Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
Co-authored-by: slaren <slarengh@gmail.com>
2023-08-23 23:08:04 +03:00
..
2023-07-25 18:35:53 +03:00
2023-07-19 10:01:11 +03:00
2023-08-23 22:37:39 +03:00
2023-08-23 17:29:09 +03:00
2023-08-22 16:03:12 +02:00
2023-08-21 23:07:43 +03:00
2023-08-21 23:07:43 +03:00
2023-08-23 17:29:09 +03:00
2023-08-22 10:56:03 +03:00
2023-08-23 23:08:04 +03:00
2023-08-21 23:07:43 +03:00
2023-08-23 23:08:04 +03:00
2023-08-23 12:57:12 +03:00
2023-08-21 23:07:43 +03:00
2023-08-21 23:07:43 +03:00
2023-08-23 17:29:09 +03:00
2023-08-21 23:07:43 +03:00
2023-08-22 14:22:08 +03:00
2023-07-06 19:17:50 +03:00
2023-03-29 20:21:09 +03:00
2023-05-03 20:58:11 +03:00
2023-05-24 09:16:22 +03:00
2023-06-15 21:05:53 +03:00
2023-03-25 21:51:41 +02:00
2023-08-21 23:07:43 +03:00
2023-04-13 16:03:39 +03:00
2023-08-23 17:29:09 +03:00
2023-07-21 13:53:27 +03:00
2023-07-21 13:53:27 +03:00
2023-08-08 14:44:48 +03:00
2023-08-08 15:07:02 +03:00
2023-08-23 17:29:09 +03:00
2023-07-21 11:13:18 +03:00
2023-08-23 17:29:09 +03:00
2023-08-23 17:29:09 +03:00