Remove gated models

README.md

@@ -17,9 +17,6 @@ preload_from_hub:
   - >-
     01-ai/Yi-Coder-1.5B-Chat
     config.json,generation_config.json,model.safetensors,special_tokens_map.json,tokenizer.model,tokenizer_config.json
-  - >-
-    google/gemma-2-2b-it
-    config.json,generation_config.json,model-00001-of-00002.safetensors,model-00002-of-00002.safetensors,model.safetensors.index.json,special_tokens_map.json,tokenizer.json,tokenizer.model,tokenizer_config.json
   - >-
     hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4
     config.json,generation_config.json,model-00001-of-00002.safetensors,model-00002-of-00002.safetensors,model.safetensors.index.json,special_tokens_map.json,tokenizer.json,tokenizer_config.json
@@ -32,9 +29,6 @@ preload_from_hub:
   - >-
     HuggingFaceTB/SmolLM2-1.7B-Instruct
     config.json,generation_config.json,merges.txt,model.safetensors,special_tokens_map.json,tokenizer.json,tokenizer_config.json,vocab.json
-  - >-
-    meta-llama/Llama-3.2-1B-Instruct
-    config.json,generation_config.json,model.safetensors,special_tokens_map.json,tokenizer.json,tokenizer_config.json
   - >-
     Qwen/Qwen2.5-0.5B-Instruct
     config.json,generation_config.json,merges.txt,model.safetensors,special_tokens_map.json,tokenizer.json,tokenizer_config.json,vocab.json
@@ -79,7 +73,3 @@ git add .
 git commit -m "Commit message"
 git push origin pr/42:refs/pr/42
 ```
-
-## Gated Models
-
-If you get an `OSError` about a model not existing, run `huggingface-cli login` to create a `~/.cache/huggingface/token` (after accepting the terms for the model on the website).

app.py

@@ -46,12 +46,10 @@ chat_interface = gr.ChatInterface(
             value="HuggingFaceTB/SmolLM2-135M-Instruct",
             choices=[
                 "01-ai/Yi-Coder-1.5B-Chat",
-                "google/gemma-2-2b-it",
                 "hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4",
                 "HuggingFaceTB/SmolLM2-135M-Instruct",
                 "HuggingFaceTB/SmolLM2-360M-Instruct",
                 "HuggingFaceTB/SmolLM2-1.7B-Instruct",
-                "meta-llama/Llama-3.2-1B-Instruct",
                 "Qwen/Qwen2.5-0.5B-Instruct",
                 "Qwen/Qwen2.5-Coder-1.5B-Instruct",
                 "THUDM/glm-edge-1.5b-chat",

lib/loader.py

@@ -37,24 +37,20 @@ class Loader:
             model_fns = {
                 # Could have used auto-classes or a pipeline
                 "01-ai/Yi-Coder-1.5B-Chat": LlamaForCausalLM.from_pretrained,
-                "google/gemma-2-2b-it": Gemma2ForCausalLM.from_pretrained,
                 "hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4": LlamaForCausalLM.from_pretrained,
                 "HuggingFaceTB/SmolLM2-135M-Instruct": LlamaForCausalLM.from_pretrained,
                 "HuggingFaceTB/SmolLM2-360M-Instruct": LlamaForCausalLM.from_pretrained,
                 "HuggingFaceTB/SmolLM2-1.7B-Instruct": LlamaForCausalLM.from_pretrained,
-                "meta-llama/Llama-3.2-1B-Instruct": LlamaForCausalLM.from_pretrained,
                 "Qwen/Qwen2.5-0.5B-Instruct": Qwen2ForCausalLM.from_pretrained,
                 "Qwen/Qwen2.5-Coder-1.5B-Instruct": Qwen2ForCausalLM.from_pretrained,
                 "THUDM/glm-edge-1.5b-chat": GlmForCausalLM.from_pretrained,
             }
             model_tokenizers = {
                 "01-ai/Yi-Coder-1.5B-Chat": LlamaTokenizer,
-                "google/gemma-2-2b-it": GemmaTokenizer,
                 "hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4": PreTrainedTokenizerFast,
                 "HuggingFaceTB/SmolLM2-135M-Instruct": GPT2Tokenizer,
                 "HuggingFaceTB/SmolLM2-360M-Instruct": GPT2Tokenizer,
                 "HuggingFaceTB/SmolLM2-1.7B-Instruct": GPT2Tokenizer,
-                "meta-llama/Llama-3.2-1B-Instruct": PreTrainedTokenizerFast,
                 "Qwen/Qwen2.5-0.5B-Instruct": Qwen2Tokenizer,
                 "Qwen/Qwen2.5-Coder-1.5B-Instruct": Qwen2Tokenizer,
                 "THUDM/glm-edge-1.5b-chat": PreTrainedTokenizerFast,