Add support for Neural-Chat, OpenChat, Orca 2, and OpenLLaMa v2, Star…

…ling LM (#926) * Update models.json Add support of Orca-2 Add support Open LLaMa Add Neural-Chat * Update README.md * Update README.md add Falcon 180B and Falcon 180B-Chat * Update README.md Add support of OpenChat 3.5 * Update models.json bugfix * Update README.md Typo fix * Update models.json Add support of Falcon 180B, Falcon 180B-Chat Add support of OpenChat 3.5 * Update README.md bugfix * Update models.json neural bugfix * Update models.json remove Falcon 180B and 180B-Chat * Update README.md remove Falcon 180B and 180B-Chat * Update models.json Add support for Starling-LM-7B-Alpha * Update README.md Add support for Starling-LM-7B-Alpha * Update models.json bugfix
serge-chat · Dec 2, 2023 · 9fabef6 · 9fabef6
1 parent a4c7e8e
commit 9fabef6
Show file tree

Hide file tree

Showing 2 changed files with 118 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -62,6 +62,11 @@ Instructions for setting up Serge on Kubernetes can be found in the [wiki](https
 | **LLaMA**  | 7B, 13B, 70B |
 | **Meditron** | 7B, 70B |
 | **Mistral** | 7B, 7B-Instruct, 7B-OpenOrca |
+| **Neural-Chat** | 7B-v3.1 | 
+| **OpenChat** | 7B-v3.5 |
+| **OpenLLaMA** | 3B-v2, 7B-v2, 13B-v2 |
+| **Orca-2** | 7B, 13B |
+| **Starling-LM** | 7B-Alpha |
 | **Vicuna** | 7B-v1.5, 13B-v1.5 |
 | **Zephyr** | 7B-Alpha, 7B-Beta |
 

diff --git a/api/src/serge/data/models.json b/api/src/serge/data/models.json
@@ -1,4 +1,117 @@
 [
+    {   
+        "name": "Starling",
+        "models": [
+            {
+                "name": "Starling-LM-7B-Alpha",
+                "repo": "TheBloke/Starling-LM-7B-alpha-GGUF",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "starling-lm-7b-alpha.Q4_K_M.gguf",
+                        "disk_space": 4370000000.0
+                    }
+                ]
+            }
+        ]
+    },    
+    {   
+        "name": "Neural-Chat",
+        "models": [
+            {
+                "name": "Neural-Chat-7B-v3-1",
+                "repo": "TheBloke/neural-chat-7B-v3-1-GGUF",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "neural-chat-7b-v3-1.Q4_K_M.gguf",
+                        "disk_space": 4370000000.0
+                    }
+                ]
+            }
+        ]
+    },
+    {   
+        "name": "OpenChat",
+        "models": [
+            {
+                "name": "OpenChat-3_5-7B",
+                "repo": "TheBloke/openchat_3.5-GGUF",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "openchat_3.5.Q4_K_M.gguf",
+                        "disk_space": 4370000000.0
+                    }
+                ]
+            }
+        ]
+    },            
+    {
+        "name": "Open_LLaMA",
+        "models": [
+            {
+                "name": "Open_LLaMA-3B-v2",
+                "repo": "maddes8cht/openlm-research-open_llama_3b_v2-gguf",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "openlm-research-open_llama_3b_v2-Q4_K_M.gguf",
+                        "disk_space": 2580000000.0
+                    }
+                ]
+            },
+            {
+                "name": "Open_LLaMA-7B-v2",
+                "repo": "maddes8cht/openlm-research-open_llama_7b_v2-gguf",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "openlm-research-open_llama_7b_v2-Q4_K_M.gguf",
+                        "disk_space": 4080000000.0
+                    }
+                ]
+            },
+            {
+                "name": "Open_LLaMA-13B-V2",
+                "repo": "maddes8cht/openlm-research-open_llama_13b-gguf",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "openlm-research-open_llama_13b-Q4_K_M.gguf",
+                        "disk_space": 7870000000.0
+                    }
+                ]
+            }            
+        ]
+    },
+    {
+        "name": "Orca-2",
+        "models": [
+            {
+                "name": "Orca-2-7B",
+                "repo": "TheBloke/Orca-2-7B-GGUF",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "orca-2-7b.Q4_K_M.gguf",
+                        "disk_space": 4080000000.0
+                    }
+                ]
+            },            
+            {
+                "name": "Orca-2-13B",
+                "repo": "TheBloke/Orca-2-13B-GGUF",
+                "files": [
+                    {
+                        "name": "q4_K_M",
+                        "filename": "orca-2-13b.Q4_K_M.gguf",
+                        "disk_space": 7870000000.0
+                    }
+                ]
+            }
+        ]
+    },    
     {
         "name": "Meditron",
         "models": [