refact, starcoder2, deepseek-coder deprecation (#674)

Author: mitya52

refact-server/README.md

@@ -108,12 +108,12 @@ Extensions > Refact.ai Assistant > Settings > Infurl
 
 | Model                                                                                                   | Completion | Chat | Fine-tuning | [Deprecated](## "Will be removed in next versions") |
 |---------------------------------------------------------------------------------------------------------|------------|------|-------------|-----------------------------------------------------|
-| [Refact/1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim)                                      | +          |      | +           |                                                     |
-| [starcoder2/3b/base](https://huggingface.co/bigcode/starcoder2-3b)                                      | +          |      | +           |                                                     |
-| [starcoder2/7b/base](https://huggingface.co/bigcode/starcoder2-7b)                                      | +          |      | +           |                                                     |
-| [starcoder2/15b/base](https://huggingface.co/bigcode/starcoder2-15b)                                    | +          |      | +           |                                                     |
-| [deepseek-coder/1.3b/base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base)                 | +          |      | +           |                                                     |
-| [deepseek-coder/5.7b/mqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base)          | +          |      | +           |                                                     |
+| [Refact/1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim)                                      | +          |      | +           | +                                                   |
+| [starcoder2/3b/base](https://huggingface.co/bigcode/starcoder2-3b)                                      | +          |      | +           | +                                                   |
+| [starcoder2/7b/base](https://huggingface.co/bigcode/starcoder2-7b)                                      | +          |      | +           | +                                                   |
+| [starcoder2/15b/base](https://huggingface.co/bigcode/starcoder2-15b)                                    | +          |      | +           | +                                                   |
+| [deepseek-coder/1.3b/base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base)                 | +          |      | +           | +                                                   |
+| [deepseek-coder/5.7b/mqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base)          | +          |      | +           | +                                                   |
 | [llama3.1/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)                    | +          | +    |             |                                                     |
 | [llama3.2/1b/instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)                         | +          | +    |             |                                                     |
 | [llama3.2/3b/instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)                         | +          | +    |             |                                                     |

refact-server/refact_known_models/huggingface.py

@@ -91,6 +91,7 @@
         "supports_scratchpads": {
             "completion": starcoder_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     "starcoder2/7b/base": {
@@ -102,6 +103,7 @@
         "supports_scratchpads": {
             "completion": starcoder_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     "starcoder2/15b/base": {
@@ -113,6 +115,7 @@
         "supports_scratchpads": {
             "completion": starcoder_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     # deepseek-coder
@@ -124,6 +127,7 @@
         "supports_scratchpads": {
             "completion": deepseek_coder_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     "deepseek-coder/5.7b/mqa-base": {
@@ -134,6 +138,7 @@
         "supports_scratchpads": {
             "completion": deepseek_coder_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     # llama

refact-server/refact_known_models/refact.py

@@ -14,6 +14,7 @@
         "supports_scratchpads": {
             "completion": refact_supports_scratchpads,
         },
+        "deprecated": True,
         "filter_caps": ["completion", "finetune"],
     },
     # "Refact/1.6B/cpu": {

refact-server/refact_utils/finetune/utils.py

@@ -13,7 +13,7 @@
 from typing import Any, Dict, Union
 
 legacy_finetune_model = "CONTRASTcode/3b/multi"
-default_finetune_model = "Refact/1.6B"
+default_finetune_model = "qwen2.5/coder/1.5b/base"
 
 
 def get_run_model_name(run_dir: str) -> str:

refact-server/refact_webgui/webgui/selfhost_model_assigner.py

@@ -265,7 +265,7 @@ def _model_inference_setup(self, inference_config: Dict[str, Any]) -> Dict[str,
     def first_run(self):
         default_config = {
             "model_assign": {
-                "Refact/1.6B": {
+                "qwen2.5/coder/1.5b/base": {
                     'gpus_shard': 1,
                     'share_gpu': True,
                 },