smollm:135m for testing purposes

smollm is a model by Hugging Face, it's good for testing and CPU inferencing. Signed-off-by: Eric Curtin <[email protected]>
rhjostone · Jan 9, 2025 · a9ecebc · a9ecebc
1 parent fbac528
commit a9ecebc
Show file tree

Hide file tree

Showing 6 changed files with 8 additions and 7 deletions.
diff --git a/README.md b/README.md
@@ -150,7 +150,7 @@ You can `list` all models pulled into local storage.
 ```
 $ ramalama list
 NAME                                                                MODIFIED     SIZE
-ollama://tiny-llm:latest                                            16 hours ago 5.5M
+ollama://smollm:135m                                            16 hours ago 5.5M
 huggingface://afrideva/Tiny-Vicuna-1B-GGUF/tiny-vicuna-1b.q2_k.gguf 14 hours ago 460M
 ollama://granite-code:3b                                            5 days ago   1.9G
 ollama://granite-code:latest                                        1 day ago    1.9G

diff --git a/docs/ramalama-list.1.md b/docs/ramalama-list.1.md
@@ -31,7 +31,7 @@ List all Models downloaded to users homedir
 ```
 $ ramalama list
 NAME                                                                MODIFIED     SIZE
-ollama://tiny-llm:latest                                            16 hours ago 5.5M
+ollama://smollm:135m                                            16 hours ago 5.5M
 huggingface://afrideva/Tiny-Vicuna-1B-GGUF/tiny-vicuna-1b.q2_k.gguf 14 hours ago 460M
 ollama://granite-code:3b                                            5 days ago   1.9G
 ollama://granite-code:latest                                        1 day ago    1.9G
@@ -41,7 +41,7 @@ ollama://moondream:latest                                           6 days ago
 List all Models in json format
 ```
 $ ramalama list --json
-{"models": [{"name": "oci://quay.io/mmortari/gguf-py-example/v1/example.gguf", "modified": 427330, "size": "4.0K"}, {"name": "huggingface://afrideva/Tiny-Vicuna-1B-GGUF/tiny-vicuna-1b.q2_k.gguf", "modified": 427333, "size": "460M"}, {"name": "ollama://tiny-llm:latest", "modified": 420833, "size": "5.5M"}, {"name": "ollama://mistral:latest", "modified": 433998, "size": "3.9G"}, {"name": "ollama://granite-code:latest", "modified": 2180483, "size": "1.9G"}, {"name": "ollama://tinyllama:latest", "modified": 364870, "size": "609M"}, {"name": "ollama://tinyllama:1.1b", "modified": 364866, "size": "609M"}]}
+{"models": [{"name": "oci://quay.io/mmortari/gguf-py-example/v1/example.gguf", "modified": 427330, "size": "4.0K"}, {"name": "huggingface://afrideva/Tiny-Vicuna-1B-GGUF/tiny-vicuna-1b.q2_k.gguf", "modified": 427333, "size": "460M"}, {"name": "ollama://smollm:135m", "modified": 420833, "size": "5.5M"}, {"name": "ollama://mistral:latest", "modified": 433998, "size": "3.9G"}, {"name": "ollama://granite-code:latest", "modified": 2180483, "size": "1.9G"}, {"name": "ollama://tinyllama:latest", "modified": 364870, "size": "609M"}, {"name": "ollama://tinyllama:1.1b", "modified": 364866, "size": "609M"}]}
 ```
 
 ## SEE ALSO

diff --git a/docs/ramalama-serve.1.md b/docs/ramalama-serve.1.md
@@ -70,7 +70,7 @@ require HTTPS and verify certificates when contacting OCI registries
 ### Run two AI Models at the same time. Notice both are running within Podman Containers.
 ```
 
-$ ramalama serve -d -p 8080 --name mymodel ollama://tiny-llm:latest
+$ ramalama serve -d -p 8080 --name mymodel ollama://smollm:135m
 09b0e0d26ed28a8418fb5cd0da641376a08c435063317e89cf8f5336baf35cfa
 
 $ ramalama serve -d -n example --port 8081 oci://quay.io/mmortari/gguf-py-example/v1/example.gguf

diff --git a/shortnames/shortnames.conf b/shortnames/shortnames.conf
@@ -5,6 +5,7 @@
   "granite:8b" = "ollama://granite3.1-dense:8b"
   "ibm/granite" = "ollama://granite3.1-dense:8b"
   "ibm/granite:2b" = "ollama://granite3.1-dense:2b"
+  "smollm:135m" = "ollama://smollm:135m"
   "ibm/granite:7b" = "huggingface://instructlab/granite-7b-lab-GGUF/granite-7b-lab-Q4_K_M.gguf"
   "ibm/granite:8b" = "ollama://granite3.1-dense:8b"
   "granite:7b" = "huggingface://instructlab/granite-7b-lab-GGUF/granite-7b-lab-Q4_K_M.gguf"

diff --git a/test/system/040-serve.bats b/test/system/040-serve.bats
@@ -66,7 +66,7 @@ verify_begin=".*run --rm -i --label RAMALAMA --security-opt=label=disable --name
     skip "Seems to cause race conditions"
     skip_if_nocontainer
 
-    model=ollama://tiny-llm:latest
+    model=ollama://smollm:135m
     container1=c_$(safename)
     container2=c_$(safename)
 
@@ -99,7 +99,7 @@ verify_begin=".*run --rm -i --label RAMALAMA --security-opt=label=disable --name
     skip "Seems to cause race conditions"
     skip_if_nocontainer
 
-    model=ollama://tiny-llm:latest
+    model=ollama://smollm:135m
     container=c_$(safename)
     port1=8100
     port2=8200

diff --git a/test/system/helpers.bash b/test/system/helpers.bash
@@ -25,7 +25,7 @@ RAMALAMA_NONLOCAL_IMAGE_FQN="$RAMALAMA_TEST_IMAGE_REGISTRY/$RAMALAMA_TEST_IMAGE_
 # Because who wants to spell that out each time?
 IMAGE=$RAMALAMA_TEST_IMAGE_FQN
 
-MODEL=ollama://ben1t0/tiny-llm:latest
+MODEL=ollama://smollm:135m
 
 load helpers.podman