Don't crash on ftype (formerly f16) == 4

[sw]

In #709 I did not add an enum value 4 for ftype (formerly f16), and made the function llama_ftype_name strict in that a LLAMA_ASSERT was raised. This made llama.cpp crash with such GPTQ model files.

Add LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4 and relax llama_ftype_name so that it returns a helpful string, which will also help future experiments with file types.

Should fix #903

[sw]

@softzer0 @thestamp @funnbot @TheBloke @wbpxre150 Inviting you to test this PR as a fix for #903

[TheBloke]

Inviting you to test this PR as a fix for #903

Working, thanks for the quick resolution!

tomj@Eddie ~/src/llama.cpp (master●●)$ time ./main -t 18 -m ../huggingface/koala-13B-GPTQ-4bit-128g-GGML/koala-13B-4bit-128g.GGML.bin --color  -c 2048 --temp 0.3 --repeat_penalty 1.2 -n -1 -i -ins
main: seed = 1681311571
llama.cpp: loading model from ../huggingface/koala-13B-GPTQ-4bit-128g-GGML/koala-13B-4bit-128g.GGML.bin
llama_model_load_internal: format     = ggjt v1 (latest)
llama_model_load_internal: n_vocab    = 32000
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 5120
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 40
llama_model_load_internal: n_layer    = 40
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: ftype      = 4 (mostly Q4_1, some F16)
llama_model_load_internal: n_ff       = 13824
llama_model_load_internal: n_parts    = 1
llama_model_load_internal: model size = 13B
llama_model_load_internal: ggml ctx size =  73.73 KB
llama_model_load_internal: mem required  = 11749.65 MB (+ 1608.00 MB per state)
llama_init_from_file: kv self size  = 1600.00 MB

system_info: n_threads = 18 / 36 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 |
main: interactive mode on.
Reverse prompt: '### Instruction:

'
sampling: temp = 0.300000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.200000
generate: n_ctx = 2048, n_batch = 8, n_predict = -1, n_keep = 2


== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to LLaMa.
 - If you want to submit another line, end your input in '\'.


> What are llamas?
Llamas are a type of animal that is native to South America. They have long necks, short legs and curved ears, and they are often used as pack animals in the Andes Mountains. Llamas are known for their calm temperament and ability to carry heavy loads over difficult terrain.
>