Merge pull request #7 from henk717/united

Merge united

aiserver.py

@@ -1,7 +1,7 @@
 #!/usr/bin/python3
 #==================================================================#
 # KoboldAI
-# Version: 1.19.1
+# Version: 1.19.2
 # By: The KoboldAI Community
 #==================================================================#
 
@@ -125,6 +125,7 @@ model_menu = {
         ["NSFW Models", "nsfwlist", "", True],
         ["Untuned OPT", "optlist", "", True],
         ["Untuned GPT-Neo/J", "gptneolist", "", True],
+        ["Untuned Pythia", "pythialist", "", True],
         ["Untuned Fairseq Dense", "fsdlist", "", True],
         ["Untuned Bloom", "bloomlist", "", True],
         ["Untuned XGLM", "xglmlist", "", True],
@@ -154,6 +155,7 @@ model_menu = {
         ["OPT Nerys 6B V2 (Hybrid)", "KoboldAI/OPT-6B-nerys-v2", "16GB", False],
         ["Janeway FSD 6.7B", "KoboldAI/fairseq-dense-6.7B-Janeway", "16GB", False],
         ["Janeway Neo 6B", "KoboldAI/GPT-J-6B-Janeway", "16GB", False],
+        ["Qilin Lit 6B (SFW)", "rexwang8/qilin-lit-6b", "16GB", False],       
         ["Janeway Neo 2.7B", "KoboldAI/GPT-Neo-2.7B-Janeway", "8GB", False],
         ["Janeway FSD 2.7B", "KoboldAI/fairseq-dense-2.7B-Janeway", "8GB", False],
         ["Nerys FSD 2.7B (Hybrid)", "KoboldAI/fairseq-dense-2.7B-Nerys", "8GB", False],
@@ -183,12 +185,31 @@ model_menu = {
         ],
     'gptneolist': [
         ["GPT-NeoX 20B", "EleutherAI/gpt-neox-20b", "64GB", False],
+        ["Pythia 13B (NeoX, Same dataset)", "EleutherAI/pythia-13b", "32GB", False],
         ["GPT-J 6B", "EleutherAI/gpt-j-6B", "16GB", False],
         ["GPT-Neo 2.7B", "EleutherAI/gpt-neo-2.7B", "8GB", False],
         ["GPT-Neo 1.3B", "EleutherAI/gpt-neo-1.3B", "6GB", False],
+        ["Pythia 800M (NeoX, Same dataset)", "EleutherAI/pythia-800m", "4GB", False],
+        ["Pythia 350M (NeoX, Same dataset)", "EleutherAI/pythia-350m", "2GB", False],
         ["GPT-Neo 125M", "EleutherAI/gpt-neo-125M", "2GB", False],
         ["Return to Main Menu", "mainmenu", "", True],
         ],
+    'pythialist': [
+        ["Pythia 13B Deduped", "EleutherAI/pythia-13b-deduped", "32GB", False],
+        ["Pythia 13B", "EleutherAI/pythia-13b", "32GB", False],
+        ["Pythia 6.7B Deduped", "EleutherAI/pythia-6.7b-deduped", "16GB", False],
+        ["Pythia 6.7B", "EleutherAI/pythia-6.7b", "16GB", False],
+        ["Pythia 1.3B Deduped", "EleutherAI/pythia-1.3b-deduped", "6GB", False],
+        ["Pythia 1.3B", "EleutherAI/pythia-1.3b", "6GB", False],
+        ["Pythia 800M", "EleutherAI/pythia-800m", "4GB", False],
+        ["Pythia 350M Deduped", "EleutherAI/pythia-350m-deduped", "2GB", False],
+        ["Pythia 350M", "EleutherAI/pythia-350m", "2GB", False],        
+        ["Pythia 125M Deduped", "EleutherAI/pythia-125m-deduped", "2GB", False],
+        ["Pythia 125M", "EleutherAI/pythia-125m", "2GB", False],
+        ["Pythia 19M Deduped", "EleutherAI/pythia-19m-deduped", "1GB", False],
+        ["Pythia 19M", "EleutherAI/pythia-19m", "1GB", False],
+        ["Return to Main Menu", "mainmenu", "", True],
+        ],
     'gpt2list': [
         ["GPT-2 XL", "gpt2-xl", "6GB", False],
         ["GPT-2 Large", "gpt2-large", "4GB", False],
@@ -996,7 +1017,7 @@ def loadmodelsettings():
     if("nobreakmodel" in js):
         vars.nobreakmodel = js["nobreakmodel"]
     if("sampler_order" in js):
-        sampler_order = vars.sampler_order
+        sampler_order = js["sampler_order"]
         if(len(sampler_order) < 7):
             sampler_order = [6] + sampler_order
         vars.sampler_order = sampler_order
@@ -1134,7 +1155,7 @@ def processsettings(js):
     if("andepth" in js):
         vars.andepth = js["andepth"]
     if("sampler_order" in js):
-        sampler_order = vars.sampler_order
+        sampler_order = js["sampler_order"]
         if(len(sampler_order) < 7):
             sampler_order = [6] + sampler_order
         vars.sampler_order = sampler_order

environments/finetuneanon.yml

@@ -1,26 +0,0 @@
-name: koboldai
-channels:
-  - pytorch
-  - conda-forge
-  - defaults
-dependencies:
-  - colorama
-  - flask-socketio
-  - flask-session
-  - pytorch
-  - cudatoolkit=11.1
-  - tensorflow-gpu
-  - python=3.8.*
-  - eventlet
-  - markdown
-  - bleach=4.1.0
-  - pip
-  - git=2.35.1
-  - marshmallow>=3.13
-  - apispec-webframeworks
-  - loguru
-  - pip:
-    - git+https://github.com/finetuneanon/transformers@gpt-neo-localattention3-rp-b
-    - flask-cloudflared
-    - flask-ngrok
-    - lupa==1.10

environments/huggingface.yml

@@ -21,6 +21,7 @@ dependencies:
   - apispec-webframeworks
   - loguru
   - termcolor
+  - psutil
   - pip:
     - flask-cloudflared
     - flask-ngrok

environments/rocm-finetune.yml

@@ -1,25 +0,0 @@
-name: koboldai-ft
-channels:
-  - conda-forge
-  - defaults
-dependencies:
-  - colorama
-  - flask-socketio
-  - flask-session
-  - python=3.8.*
-  - eventlet
-  - markdown
-  - bleach=4.1.0
-  - pip
-  - git=2.35.1
-  - marshmallow>=3.13
-  - apispec-webframeworks
-  - loguru
-  - pip:
-    - --find-links https://download.pytorch.org/whl/rocm4.2/torch_stable.html
-    - torch
-    - torchvision==0.11.1
-    - flask-cloudflared
-    - git+https://github.com/finetuneanon/transformers@gpt-neo-localattention3-rp-b
-    - flask-ngrok
-    - lupa==1.10

environments/rocm.yml

@@ -18,6 +18,7 @@ dependencies:
   - apispec-webframeworks
   - loguru
   - termcolor
+  - psutil
   - pip:
     - --extra-index-url https://download.pytorch.org/whl/rocm5.1.1
     - torch

maps/gptj.json

@@ -9,11 +9,11 @@
   },
   "static_weights": {
     "transformer.wte.weight": {"mtj": {"module": "embedding_shard/~/linear", "param": "w", "transforms": ["no_transpose", "vocab_pad"]}},
-    "transformer.wte.bias": {"mtj": {"module": "embedding_shard/~/linear", "param": "b"}},
+    "transformer.wte.bias": {"mtj": {"module": "embedding_shard/~/linear", "param": "b", "transforms": ["vocab_pad"]}},
     "transformer.ln_f.weight": {"mtj": {"module": "projection_shard/~/replicated_layer_norm", "param": "scale"}},
     "transformer.ln_f.bias": {"mtj": {"module": "projection_shard/~/replicated_layer_norm", "param": "offset"}},
     "lm_head.weight": {"mtj": {"module": "projection_shard/~/linear", "param": "w", "transforms": ["vocab_pad"]}},
-    "lm_head.bias": {"mtj": {"module": "projection_shard/~/linear", "param": "b"}}
+    "lm_head.bias": {"mtj": {"module": "projection_shard/~/linear", "param": "b", "transforms": ["vocab_pad"]}}
   },
   "layer_weights": {
     "transformer.h.{layer}.attn.bias": {},

play.bat

@@ -2,6 +2,8 @@
 cd /D %~dp0
 SET CONDA_SHLVL=
 
+rmdir /S /Q flask_session
+
 TITLE KoboldAI - Server
 SET /P M=<loader.settings
 IF %M%==1 GOTO drivemap

tpu_mtj_backend.py

@@ -1149,7 +1149,8 @@ def load_model(path: str, driver_version="tpu_driver0.1_dev20210607", hf_checkpo
             params[param] = default_params[param]
 
     # Use an optimization that will allow us to avoid one extra transpose operation
-    params["transposed_linear"] = True
+    if hf_checkpoint:
+        params["transposed_linear"] = True
 
     # Load tokenizer
     if vars.model == "TPUMeshTransformerGPTNeoX":
@@ -1307,7 +1308,7 @@ def load_model(path: str, driver_version="tpu_driver0.1_dev20210607", hf_checkpo
                     if "divide_by_shards" in transforms:
                         tensor /= params["cores_per_replica"]
                     if "vocab_pad" in transforms:
-                        tensor = torch.nn.functional.pad(tensor, (0, 0, 0, params["n_vocab_padding"]))
+                        tensor = torch.nn.functional.pad(tensor, (0,) * (tensor.ndim * 2 - 1) + (params["n_vocab_padding"],))
                     # We don't need to transpose linear module weights anymore because MTJ will do it for us if `transposed_linear` is set to True in the config
                     #if "no_transpose" not in transforms and tensor.ndim == 2:
                     #    tensor = tensor.T