Upload folder using huggingface_hub

modeling_internvl_chat.py

@@ -375,7 +375,7 @@ class InternVLChatModel(PreTrainedModel):
         vit_embeds = self.mlp1(vit_embeds)
         return vit_embeds
 
-    def chat(self, tokenizer, pixel_values, question, generation_config,
+    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
              IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'):
 
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
@@ -384,8 +384,15 @@ class InternVLChatModel(PreTrainedModel):
         from .conversation import get_conv_template
 
         template = get_conv_template(self.template)
-        image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token + IMG_END_TOKEN
-        template.append_message(template.roles[0], image_tokens + '\n' + question)
+        if history is None:
+            history = []
+            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token + IMG_END_TOKEN
+            question = image_tokens + '\n' + question
+        else:
+            for (old_question, old_answer) in history:
+                template.append_message(template.roles[0], old_question)
+                template.append_message(template.roles[1], old_answer)
+        template.append_message(template.roles[0], question)
         template.append_message(template.roles[1], None)
         query = template.get_prompt()
         model_inputs = tokenizer(query, return_tensors='pt')
@@ -399,9 +406,11 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        query_to_print = query.replace(image_tokens, '<image>')
-        print(query_to_print, response)
-        return response
+        history.append((question, response))
+        if return_history:
+            return response, history
+        else:
+            return response
 
     @torch.no_grad()
     def generate(

runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/events.out.tfevents.1708234550.SH-IDC1-10-140-37-8.124298.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0813499a41ad34fcc8faf77fee66dc139237be21fbd16e9abfaab6d39aebb8a
+size 8764

runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/events.out.tfevents.1708237619.SH-IDC1-10-140-37-8.185381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf844c1015f2b40fa8e152da5dce2540ea0f210cbcc59c30e0bf70be62d85f7
+size 507325