Update models

Signed-off-by: Xin Liu <[email protected]>

README.md

@@ -41,13 +41,17 @@ quantized_by: Second State Inc.
 
 - Context size: `3072`
 
-<!-- - Run as LlamaEdge service
+- Run as LlamaEdge service
 
   ```bash
-  wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-7b-it-Q5_K_M.gguf llama-api-server.wasm -p gemma-instruct -c 4096
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-7b-it-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template gemma-instruct \
+    --ctx-size 3072 \
+    --model-name gemma-1.1-7b
   ```
 
-- Run as LlamaEdge command app
+<!-- - Run as LlamaEdge command app
 
   ```bash
   wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-7b-it-Q5_K_M.gguf llama-chat.wasm -p gemma-instruct -c 4096
@@ -71,4 +75,4 @@ quantized_by: Second State Inc.
 | [gemma-1.1-7b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q8_0.gguf)     | Q8_0   | 8 | 9.08 GB| very large, extremely low quality loss - not recommended |
 | [gemma-1.1-7b-it-f16.gguf](https://huggingface.co/second-state/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-f16.gguf)     | f16   | 16 | 34.2 GB|  |
 
-*Quantized with llama.cpp b2534*
+*Quantized with llama.cpp b2589*

gemma-1.1-7b-it-Q2_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4a940efdcc468736b1764bc90d16b23f88314b1ea95935ce839c736d59166d
-size 3481447424
+oid sha256:b9cc84d76e1db3e9e054a7692f837f79177721a20d5dcdb1103d3e043d5a91d0
+size 3481447392

gemma-1.1-7b-it-Q3_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b85e8d1fbf55504367df3aa9706d82aed29fb23f4ef595775ae17cc53ff6c7
-size 4709067776
+oid sha256:0140da983c11e342b46ccedec9b82220c2efe54fe5bda3d1c20bf445d677b1fa
+size 4709067744

gemma-1.1-7b-it-Q3_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d140fb6359595da6fc8bc46d343b76800a4b1fbf7040a54bb013670f951e3a72
-size 4369329152
+oid sha256:8ca97bd41f823cd56954b23f1ebd5b5edb9145fc201f108c4486f2d98db2faac
+size 4369329120

gemma-1.1-7b-it-Q3_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e698c5fe5c1ce84b3f3a4ba92d565c727eb3e32a4c3c2e07ea140859d3bdd9ca
-size 3982404608
+oid sha256:509ea44fbc8ffe021e920d9b788cfab0d3f6c342f46f0043096269881a68cdbf
+size 3982404576

gemma-1.1-7b-it-Q4_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4613de65cc03ab74069d7362dbeee2c134093e05d0cd61a6c5a56076e446a7fb
-size 5011844096
+oid sha256:f7bea5456d3116ccb9c260f843de52980ab261e4638e827dcc50e0b5ccb80bad
+size 5011844064

gemma-1.1-7b-it-Q4_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680e96f3bc3400cd0b4c7cc823758afb98f5d44b06ffb5fe21ee37fd95c74aa6
-size 5329759232
+oid sha256:87b5061a63b7229dab43454d3d8314fcd422e21a53664d3b47c68ffd5c92d2e7
+size 5329759200

gemma-1.1-7b-it-Q4_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013d926d89a09eb6b50ce3e925e009e4eaf05e3da4c300c8a1781cd514a9f866
-size 5046447104
+oid sha256:669c00d0a65f83971986c3cc727cfeeb2be0011dc0fd455ca48bafdfacb9e7a1
+size 5046447072

gemma-1.1-7b-it-Q5_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1e9da4d1e2b5908da8532da1f78112a5879369d6a1a3bfc6ff796c7fa68e2d
-size 5980728320
+oid sha256:cb314ce447ac0f60c18cd5d8c36e0ef9cfb47ab3b5cc23aa167c11b2a499cb90
+size 5980728288

gemma-1.1-7b-it-Q5_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62b6d5a0d00e76709217fcccc48c1680a74be2ec9fe2300b17e1c7f84669a8a
-size 6144502784
+oid sha256:aa05718f43a503beb5982cc772b18d6518a8947f8caf7dcc99aef5452b5a66c2
+size 6144502752

gemma-1.1-7b-it-Q5_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe0027e846c63d67dfded677c49aa08f7aced3060d1a1fd7740197ddad92a19
-size 5980728320
+oid sha256:cb5354bdb0e50c2633640c5fa48d15960fd00108f60845ee8858ee549104aaf9
+size 5980728288

gemma-1.1-7b-it-Q6_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660b4c9bf162dd80091ca9840513d65caf3ee026fb2b634961f2d2b3e6d326b9
-size 7010167808
+oid sha256:04fb3e9a78142df5f7352cf2cf5e6cc3a060937bdc131af55e266afed43ebf7f
+size 7010167776

gemma-1.1-7b-it-Q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5da21f32dfb0c7f7cae8e252ab6d84e1bbaa44924c7a1343761de1afdfabba3
-size 9077844992
+oid sha256:70840b7af2b7191b0088c7c2139e9f829324c03ad808f52db5578b4d03e9272c
+size 9077844960

gemma-1.1-7b-it-f16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312d10dbb653bd8d4ab3ec68f83efc61f947d268eba6baca97892d5c7834d910
-size 34156768192
+oid sha256:8374dc9da250dffb1ef78505964e8c072fe6688882f93dd72cb870c8a6f0981b
+size 17081756608