Hello

#1
by mirek190 - opened

I trying to load that ggml via koboldccp but getting error

Identified as GPT-NEO-X model: (ver 401)
Attempting to Load...

System Info: AVX = 1 | 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 | VSX = 0 |
stablelm_model_load: loading model from 'F:\LLAMA\llama.cpp\models\starcoder-13b-q4_1.bin' - please wait ...
stablelm_model_load: n_vocab = 49152
stablelm_model_load: n_ctx = 8192
stablelm_model_load: n_embd = 6144
stablelm_model_load: n_head = 48
stablelm_model_load: n_layer = 40
stablelm_model_load: n_rot = 3
stablelm_model_load: ftype = 49152
GGML_ASSERT: ggml.c:4638: wtype != GGML_TYPE_COUNT

How to run it?

how to run that starcoder ggml?

Sign up or log in to comment