diff --git a/characters/instruction-following/Airoboros-v1.2.yaml b/characters/instruction-following/Airoboros-v1.2.yaml
new file mode 100644
index 00000000..7f1bfed6
--- /dev/null
+++ b/characters/instruction-following/Airoboros-v1.2.yaml
@@ -0,0 +1,4 @@
+user: "USER:"
+bot: "ASSISTANT:"
+turn_template: "<|user|> <|user-message|>\n<|bot|> <|bot-message|>\n"
+context: "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.\n"
diff --git a/characters/instruction-following/Llama-v2.yaml b/characters/instruction-following/Llama-v2.yaml
new file mode 100644
index 00000000..3c1e27a9
--- /dev/null
+++ b/characters/instruction-following/Llama-v2.yaml
@@ -0,0 +1,4 @@
+user: ""
+bot: ""
+turn_template: "<|user|><|user-message|> [/INST] <|bot|><|bot-message|> [INST] "
+context: "[INST] <<SYS>>\nAnswer the questions.\n<</SYS>>\n"
diff --git a/docs/GPTQ-models-(4-bit-mode).md b/docs/GPTQ-models-(4-bit-mode).md
index 63a6ed5b..838595ef 100644
--- a/docs/GPTQ-models-(4-bit-mode).md
+++ b/docs/GPTQ-models-(4-bit-mode).md
@@ -142,12 +142,25 @@ python setup_cuda.py install
 
 ### Getting pre-converted LLaMA weights
 
-These are models that you can simply download and place in your `models` folder.
+* Direct download (recommended):
 
-* Converted without `group-size` (better for the 7b model): https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1483891617
-* Converted with `group-size` (better from 13b upwards): https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1483941105 
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-7B-4bit-128g
 
-⚠️ The tokenizer files in the sources above may be outdated. Make sure to obtain the universal LLaMA tokenizer as described [here](https://github.com/oobabooga/text-generation-webui/blob/main/docs/LLaMA-model.md#option-1-pre-converted-weights).
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-13B-4bit-128g
+
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-30B-4bit-128g
+
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-65B-4bit-128g
+
+These models were converted with `desc_act=True`. They work just fine with ExLlama. For AutoGPTQ, they will only work on Linux with the `triton` option checked.
+
+* Torrent:
+
+https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1483891617
+
+https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1483941105
+
+These models were converted with `desc_act=False`. As such, they are less accurate, but they work with AutoGPTQ on Windows. The `128g` versions are better from 13b upwards, and worse for 7b. The tokenizer files in the torrents are outdated, in particular the files called `tokenizer_config.json` and `special_tokens_map.json`. Here you can find those files: https://huggingface.co/oobabooga/llama-tokenizer
 
 ### Starting the web UI:
 
diff --git a/docs/LLaMA-model.md b/docs/LLaMA-model.md
index cd655268..ba7350f5 100644
--- a/docs/LLaMA-model.md
+++ b/docs/LLaMA-model.md
@@ -9,10 +9,21 @@ This guide will cover usage through the official `transformers` implementation.
 
 ### Option 1: pre-converted weights
 
-* Torrent: https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1484235789
-* Direct download: https://huggingface.co/Neko-Institute-of-Science
+* Direct download (recommended):
 
-⚠️ The tokenizers for the Torrent source above and also for many LLaMA fine-tunes available on Hugging Face may be outdated, in particular the files called `tokenizer_config.json` and `special_tokens_map.json`. Here you can find those files: https://huggingface.co/oobabooga/llama-tokenizer
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-7B-HF
+
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-13B-HF
+
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-30B-HF
+
+https://huggingface.co/Neko-Institute-of-Science/LLaMA-65B-HF
+
+* Torrent:
+
+https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1484235789
+
+The tokenizer files in the torrent above are outdated, in particular the files called `tokenizer_config.json` and `special_tokens_map.json`. Here you can find those files: https://huggingface.co/oobabooga/llama-tokenizer
 
 ### Option 2: convert the weights yourself
 
diff --git a/docs/LLaMA-v2-model.md b/docs/LLaMA-v2-model.md
new file mode 100644
index 00000000..55c6aa76
--- /dev/null
+++ b/docs/LLaMA-v2-model.md
@@ -0,0 +1,35 @@
+# LLaMA-v2
+
+To convert LLaMA-v2 from the `.pth` format provided by Meta to transformers format, follow the steps below:
+
+1) `cd` into your `llama` folder (the one containing `download.sh` and the models that you downloaded):
+
+```
+cd llama
+```
+
+2) Clone the transformers library:
+
+```
+git clone 'https://github.com/huggingface/transformers'
+
+```
+
+3) Create symbolic links from the downloaded folders to names that the conversion script can recognize:
+
+```
+ln -s llama-2-7b 7B
+ln -s llama-2-13b 13B
+```
+
+4) Do the conversions:
+
+```
+mkdir llama-2-7b-hf llama-2-13b-hf
+python ./transformers/src/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir . --model_size 7B --output_dir llama-2-7b-hf --safe_serialization true
+python ./transformers/src/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir . --model_size 13B --output_dir llama-2-13b-hf --safe_serialization true
+```
+
+5) Move the output folders inside `text-generation-webui/models`
+
+6) Have fun
diff --git a/models/config.yaml b/models/config.yaml
index 37e4273c..1cc5605c 100644
--- a/models/config.yaml
+++ b/models/config.yaml
@@ -186,6 +186,9 @@ llama-65b-gptq-3bit:
 .*airoboros:
   mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
+.*airoboros.*1.2:
+  mode: 'instruct'
+  instruction_template: 'Airoboros-v1.2'
 .*WizardLM-30B-V1.0:
   mode: 'instruct'
   instruction_template: 'Vicuna-v1.1'
@@ -269,3 +272,8 @@ TheBloke_WizardLM-30B-GPTQ:
 .*godzilla:
   mode: 'instruct'
   instruction_template: 'Alpaca'
+.*llama-(2|v2):
+  truncation_length: 4096
+.*llama-(2|v2).*chat:
+  mode: 'instruct'
+  instruction_template: 'Llama-v2'
diff --git a/modules/LoRA.py b/modules/LoRA.py
index 0626c969..1350783f 100644
--- a/modules/LoRA.py
+++ b/modules/LoRA.py
@@ -132,7 +132,7 @@ def add_lora_transformers(lora_names):
         if not shared.args.load_in_8bit and not shared.args.cpu:
             shared.model.half()
             if not hasattr(shared.model, "hf_device_map"):
-                if torch.has_mps:
+                if torch.backends.mps.is_available():
                     device = torch.device('mps')
                     shared.model = shared.model.to(device)
                 else:
diff --git a/modules/llamacpp_hf.py b/modules/llamacpp_hf.py
index 12212fec..94d893c4 100644
--- a/modules/llamacpp_hf.py
+++ b/modules/llamacpp_hf.py
@@ -42,7 +42,6 @@ class LlamacppHF(PreTrainedModel):
 
         # Make the forward call
         seq_tensor = torch.tensor(seq)
-        self.cache = seq_tensor
         if labels is None:
             if self.cache is None or not torch.equal(self.cache, seq_tensor[:-1]):
                 self.model.reset()
@@ -50,13 +49,15 @@ class LlamacppHF(PreTrainedModel):
             else:
                 self.model.eval([seq[-1]])
 
-            logits = torch.tensor(self.model.eval_logits)[-1].view(1, 1, -1).to(kwargs['input_ids'].device)
+            logits = torch.tensor(self.model.eval_logits[-1]).view(1, 1, -1).to(kwargs['input_ids'].device)
         else:
             self.model.reset()
             self.model.eval(seq)
             logits = torch.tensor(self.model.eval_logits)
             logits = logits.view(1, logits.shape[0], logits.shape[1]).to(kwargs['input_ids'].device)
 
+        self.cache = seq_tensor
+
         # Based on transformers/models/llama/modeling_llama.py
         loss = None
         if labels is not None:
@@ -96,6 +97,8 @@ class LlamacppHF(PreTrainedModel):
             'use_mlock': shared.args.mlock,
             'low_vram': shared.args.low_vram,
             'n_gpu_layers': shared.args.n_gpu_layers,
+            'rope_freq_base': 10000 * shared.args.alpha_value ** (64/63.),
+            'rope_freq_scale': 1.0 / shared.args.compress_pos_emb,
             'logits_all': True,
         }
 
diff --git a/modules/llamacpp_model.py b/modules/llamacpp_model.py
index 86537a27..180b0f37 100644
--- a/modules/llamacpp_model.py
+++ b/modules/llamacpp_model.py
@@ -50,7 +50,9 @@ class LlamaCppModel:
             'use_mmap': not shared.args.no_mmap,
             'use_mlock': shared.args.mlock,
             'low_vram': shared.args.low_vram,
-            'n_gpu_layers': shared.args.n_gpu_layers
+            'n_gpu_layers': shared.args.n_gpu_layers,
+            'rope_freq_base': 10000 * shared.args.alpha_value ** (64/63.),
+            'rope_freq_scale': 1.0 / shared.args.compress_pos_emb,
         }
 
         result.model = Llama(**params)
diff --git a/modules/loaders.py b/modules/loaders.py
index da38c2f5..b760128f 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -37,6 +37,8 @@ loaders_and_params = {
         'low_vram',
         'mlock',
         'llama_cpp_seed',
+        'compress_pos_emb',
+        'alpha_value',
     ],
     'llamacpp_HF': [
         'n_ctx',
@@ -47,6 +49,8 @@ loaders_and_params = {
         'low_vram',
         'mlock',
         'llama_cpp_seed',
+        'compress_pos_emb',
+        'alpha_value',
         'llamacpp_HF_info',
     ],
     'Transformers': [
diff --git a/modules/models.py b/modules/models.py
index 9d9ba951..232d5fa6 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -147,7 +147,7 @@ def huggingface_loader(model_name):
     # Load the model in simple 16-bit mode by default
     if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.load_in_4bit, shared.args.auto_devices, shared.args.disk, shared.args.deepspeed, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None]):
         model = LoaderClass.from_pretrained(Path(f"{shared.args.model_dir}/{model_name}"), low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16, trust_remote_code=shared.args.trust_remote_code)
-        if torch.has_mps:
+        if torch.backends.mps.is_available():
             device = torch.device('mps')
             model = model.to(device)
         else:
@@ -167,7 +167,7 @@ def huggingface_loader(model_name):
             "trust_remote_code": shared.args.trust_remote_code
         }
 
-        if not any((shared.args.cpu, torch.cuda.is_available(), torch.has_mps)):
+        if not any((shared.args.cpu, torch.cuda.is_available(), torch.backends.mps.is_available())):
             logger.warning("torch.cuda.is_available() returned False. This means that no GPU has been detected. Falling back to CPU mode.")
             shared.args.cpu = True
 
diff --git a/modules/shared.py b/modules/shared.py
index f20b9fcd..08d88ff5 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -32,10 +32,10 @@ need_restart = False
 
 settings = {
     'dark_theme': False,
-    'autoload_model': True,
+    'autoload_model': False,
     'max_new_tokens': 200,
     'max_new_tokens_min': 1,
-    'max_new_tokens_max': 2000,
+    'max_new_tokens_max': 4096,
     'seed': -1,
     'character': 'None',
     'name1': 'You',
diff --git a/modules/text_generation.py b/modules/text_generation.py
index 566c2f55..d3939d3f 100644
--- a/modules/text_generation.py
+++ b/modules/text_generation.py
@@ -57,7 +57,7 @@ def encode(prompt, add_special_tokens=True, add_bos_token=True, truncation_lengt
         return input_ids.numpy()
     elif shared.args.deepspeed:
         return input_ids.to(device=local_rank)
-    elif torch.has_mps:
+    elif torch.backends.mps.is_available():
         device = torch.device('mps')
         return input_ids.to(device)
     else:
diff --git a/requirements.txt b/requirements.txt
index 24aa6d79..40ede730 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-accelerate==0.20.3
+accelerate==0.21.0
 colorama
 datasets
 einops
@@ -20,11 +20,11 @@ tensorboard
 wandb
 transformers==4.30.2
 git+https://github.com/huggingface/peft@03eb378eb914fbee709ff7c86ba5b1d033b89524
-bitsandbytes==0.40.1.post1; platform_system != "Windows"
-https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.40.1.post1-py3-none-win_amd64.whl; platform_system == "Windows"
+bitsandbytes==0.40.2; platform_system != "Windows"
+https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.40.2-py3-none-win_amd64.whl; platform_system == "Windows"
 llama-cpp-python==0.1.72; platform_system != "Windows"
 https://github.com/abetlen/llama-cpp-python/releases/download/v0.1.72/llama_cpp_python-0.1.72-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.2.2/auto_gptq-0.2.2+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.2.2/auto_gptq-0.2.2+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.3.0/auto_gptq-0.3.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.3.0/auto_gptq-0.3.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/exllama/releases/download/0.0.6/exllama-0.0.6+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/exllama/releases/download/0.0.6/exllama-0.0.6+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/server.py b/server.py
index 727e5894..babdec2d 100644
--- a/server.py
+++ b/server.py
@@ -277,20 +277,17 @@ def create_model_menus():
     load.click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         update_model_parameters, gradio('interface_state'), None).then(
-        partial(load_model_wrapper, autoload=True), gradio('model_menu', 'loader'), gradio('model_status'), show_progress=False).then(
-        lambda: shared.lora_names, None, gradio('lora_menu'))
+        partial(load_model_wrapper, autoload=True), gradio('model_menu', 'loader'), gradio('model_status'), show_progress=False)
 
     unload.click(
         unload_model, None, None).then(
-        lambda: "Model unloaded", None, gradio('model_status')).then(
-        lambda: shared.lora_names, None, gradio('lora_menu'))
+        lambda: "Model unloaded", None, gradio('model_status'))
 
     reload.click(
         unload_model, None, None).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         update_model_parameters, gradio('interface_state'), None).then(
-        partial(load_model_wrapper, autoload=True), gradio('model_menu', 'loader'), gradio('model_status'), show_progress=False).then(
-        lambda: shared.lora_names, None, gradio('lora_menu'))
+        partial(load_model_wrapper, autoload=True), gradio('model_menu', 'loader'), gradio('model_status'), show_progress=False)
 
     save_settings.click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
@@ -1128,10 +1125,6 @@ if __name__ == "__main__":
     if shared.args.model is not None:
         shared.model_name = shared.args.model
 
-    # Only one model is available
-    elif len(available_models) == 1:
-        shared.model_name = available_models[0]
-
     # Select the model from a command-line menu
     elif shared.args.model_menu:
         if len(available_models) == 0:
diff --git a/settings-template.yaml b/settings-template.yaml
index e949f697..ef9a7e7e 100644
--- a/settings-template.yaml
+++ b/settings-template.yaml
@@ -1,8 +1,8 @@
 dark_theme: false
-autoload_model: true
+autoload_model: false
 max_new_tokens: 200
 max_new_tokens_min: 1
-max_new_tokens_max: 2000
+max_new_tokens_max: 4096
 seed: -1
 character: None
 name1: You