ngxson HF staff commited on
Commit
37cbc65
1 Parent(s): d4ee4f1

update model files

Browse files
README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ # Speculative decoding with Qwen 32B + Qwen 1.5B
2
+
3
+ Example:
4
+
5
+ ```sh
6
+ llama-server \
7
+ -m qwen2.5-coder-32b-instruct-q4_k_m.gguf \
8
+ -md qwen2.5-coder-1.5b-instruct-q4_k_m.gguf \
9
+ --ctx-size 65536
10
+ ```
qwen2.5-coder-1.5b-instruct-q4_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc324af070c2ecbfd324a30884d2f951a7ff756aba85cb811a6ec436933bb046
3
+ size 1117320768
qwen2.5-coder-32b-instruct-q4_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d64b316b5e6319d9613e0d97935d9ebd631fc7e334da400d00085eca749d085
3
+ size 19851335872