add model

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llama-cli filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,9 @@
 # This is a 4-bit quantized ggml file for use with [llama.cpp](https://github.com/ggerganov/llama.cpp) on the CPU (pre-mmap)
 
-Original model: https://github.com/pointnetwork/point-alpaca
+Original model: https://github.com/pointnetwork/point-alpaca
+
+# How to run
+
+./llama-cli -m ./ggml-model-q4_0.bin -f ./alpaca_prompt.txt --repl
+
+(`llama-cli` is built from https://github.com/rustformers/llama-rs/tree/57440bffb0d946acf73b37e85498c77fc9dfe715)

alpaca_prompt.txt

@@ -0,0 +1,7 @@
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+
+{{PROMPT}}
+
+### Response:

ggml-model-q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c253cee1be896fdac925bf8c41463b6496ec83fe9c049bd0cd565fb7b36f6c7
+size 4212855021

llama-cli

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bf8a8669451605c6288aa3567050d4658f40653819bbef4f7dd8512e35f8b3
+size 7592512

params.json

@@ -0,0 +1 @@
+{"dim": 4096, "multiple_of": 256, "n_heads": 32, "n_layers": 32, "norm_eps": 1e-06, "vocab_size": 32000}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723