First model version

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,90 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "damp_percent": 0.1,
+    "dataset": [
+      "Human: I had a dream about us last night. It was so real, I woke up smiling.\nAssistant: MSG1: I had a dream about us last night. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It was so real, I woke up smiling. \\| DELAY2: 3 \\| DELAY_REASON2: building intrigue",
+      "Human: I'm at our favorite caf\u00e9 and it feels empty without you here. Missing you.\nAssistant: MSG1: I'm at our favorite caf\u00e9 right now. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It feels empty without you here. Missing you. \\| DELAY2: 4 \\| DELAY_REASON2: expressing feelings",
+      "Human: You won't believe what just happened at work! It's absolutely crazy.\nAssistant: MSG1: You won't believe what just happened at work! \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It's absolutely crazy. \\| DELAY2: 3 \\| DELAY_REASON2: building excitement",
+      "Human: Remember that movie we talked about? Guess what, I got tickets for us!\nAssistant: MSG1: Remember that movie we talked about? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Guess what, I got tickets for us! \\| DELAY2: 4 \\| DELAY_REASON2: revealing a surprise",
+      "Human: Cooking dinner tonight, wish you were here to taste test. \ud83c\udf72\nAssistant: MSG1: Cooking dinner tonight. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Wish you were here to taste test. \ud83c\udf72 \\| DELAY2: 3 \\| DELAY_REASON2: sharing a moment",
+      "Human: Just passed by that bookstore you love. Made me think of you immediately.\nAssistant: MSG1: Just passed by that bookstore you love. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Made me think of you immediately. \\| DELAY2: 4 \\| DELAY_REASON2: conveying affection",
+      "Human: Had a tough day. Really could use one of your hugs right now.\nAssistant: MSG1: Had a tough day. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Really could use one of your hugs right now. \\| DELAY2: 5 \\| DELAY_REASON2: seeking comfort",
+      "Human: You know what? I'm really lucky to have you in my life.\nAssistant: MSG1: You know what? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: I'm really lucky to have you in my life. \\| DELAY2: 3 \\| DELAY_REASON2: expressing gratitude and love",
+      "Human: Watching our show without you just isn't the same. Can't wait to watch it together again.\nAssistant: MSG1: Watching our show without you. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Just isn't the same. Can't wait to watch it together again. \\| DELAY2: 5 \\| DELAY_REASON2: sharing experiences and anticipation",
+      "Human: I was thinking about our last trip, remember that sunset on the beach? It was so beautiful, just like you. It made me realize how much I enjoy our adventures together. Can't wait for our next one.\nAssistant: MSG1: I was thinking about our last trip, remember that sunset on the beach? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It was so beautiful, just like you. \\| DELAY2: 3 \\| DELAY_REASON2: sharing a memory\nMSG3: It made me realize how much I enjoy our adventures together. \\| DELAY3: 6 \\| DELAY_REASON3: expressing feelings\nMSG4: Can't wait for our next one. \\| DELAY4: 3 \\| DELAY_REASON4: looking forward to future plans",
+      "Human: Just saw a shooting star and made a wish for us.\nAssistant: MSG1: Just saw a shooting star and made a wish for us. \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+      "Human: Your favorite song is playing on the radio, made me smile.\nAssistant: MSG1: Your favorite song is playing on the radio, made me smile. \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+      "Human: Found that book you mentioned, picking it up for you!\nAssistant: MSG1: Found that book you mentioned, picking it up for you! \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+      "Human: Hey, how's your day going? Just finished a meeting, thought of calling you. Let's catch up tonight?\nAssistant: MSG1: Hey, how's your day going? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Just finished a meeting, thought of calling you. \\| DELAY2: 4 \\| DELAY_REASON2: natural conversation flow\nMSG3: Let's catch up tonight? \\| DELAY3: 5 \\| DELAY_REASON3: proposing a plan",
+      "Human: Woke up missing you more than usual today. What are you up to? Maybe we can meet later.\nAssistant: MSG1: Woke up missing you more than usual today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: What are you up to? \\| DELAY2: 3 \\| DELAY_REASON2: showing interest\nMSG3: Maybe we can meet later. \\| DELAY3: 6 \\| DELAY_REASON3: suggesting a meeting",
+      "Human: Hey, just got back from the gym. Feeling pumped!\nAssistant: MSG1: Hey, just got back from the gym. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling pumped! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+      "Human: I tried making that dish you love for dinner. Nailed it!\nAssistant: MSG1: I tried making that dish you love for dinner. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Nailed it! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Stuck in traffic again. This commute is killing me.\nAssistant: MSG1: Stuck in traffic again. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: This commute is killing me. \\| DELAY2: 4 \\| DELAY_REASON2: expressing frustration",
+      "Human: Just finished reading that book you recommended. Couldn't put it down!\nAssistant: MSG1: Just finished reading that book you recommended. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Couldn't put it down! \\| DELAY2: 3 \\| DELAY_REASON2: sharing enthusiasm",
+      "Human: Missed my morning coffee today. Feeling groggy.\nAssistant: MSG1: Missed my morning coffee today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling groggy. \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+      "Human: Just finished my last exam of the semester. Time to celebrate!\nAssistant: MSG1: Just finished my last exam of the semester. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Time to celebrate! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Ran into an old friend today. Brought back so many memories.\nAssistant: MSG1: Ran into an old friend today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Brought back so many memories. \\| DELAY2: 4 \\| DELAY_REASON2: reminiscing",
+      "Human: Planning a surprise party for your birthday. Can't wait to see your reaction!\nAssistant: MSG1: Planning a surprise party for your birthday. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Can't wait to see your reaction! \\| DELAY2: 4 \\| DELAY_REASON2: anticipating excitement",
+      "Human: Just got promoted at work! Hard work pays off.\nAssistant: MSG1: Just got promoted at work! \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Hard work pays off. \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Feeling stressed out lately. Need a break.\nAssistant: MSG1: Feeling stressed out lately. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Need a break. \\| DELAY2: 3 \\| DELAY_REASON2: expressing need for relaxation",
+      "Human: Just finished my morning workout. Feeling energized!\nAssistant: MSG1: Just finished my morning workout. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling energized! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+      "Human: Finally got around to organizing my closet. Feels so satisfying.\nAssistant: MSG1: Finally got around to organizing my closet. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feels so satisfying. \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Traffic is insane today. Already late for my meeting.\nAssistant: MSG1: Traffic is insane today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Already late for my meeting. \\| DELAY2: 4 \\| DELAY_REASON2: expressing frustration",
+      "Human: Tried a new recipe for lunch. Turned out better than expected!\nAssistant: MSG1: Tried a new recipe for lunch. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Turned out better than expected! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Feeling a bit under the weather today. Need some rest.\nAssistant: MSG1: Feeling a bit under the weather today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Need some rest. \\| DELAY2: 3 \\| DELAY_REASON2: expressing need for relaxation",
+      "Human: Finished reading a great book last night. Highly recommend it.\nAssistant: MSG1: Finished reading a great book last night. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Highly recommend it. \\| DELAY2: 3 \\| DELAY_REASON2: sharing enthusiasm",
+      "Human: Attended a fascinating lecture this afternoon. Feeling inspired!\nAssistant: MSG1: Attended a fascinating lecture this afternoon. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling inspired! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+      "Human: Can't believe it's already Friday. Any plans for the weekend?\nAssistant: MSG1: Can't believe it's already Friday. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Any plans for the weekend? \\| DELAY2: 4 \\| DELAY_REASON2: natural conversation flow",
+      "Human: Finished a big project at work. Time to celebrate!\nAssistant: MSG1: Finished a big project at work. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Time to celebrate! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+      "Human: Just signed up for a new fitness class. Excited to try it out!\nAssistant: MSG1: Just signed up for a new fitness class. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Excited to try it out! \\| DELAY2: 3 \\| DELAY_REASON2: sharing anticipation"
+    ],
+    "desc_act": false,
+    "disable_exllama": true,
+    "group_size": 128,
+    "model_seqlen": 4096,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens",
+      "model.embed_dropout"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeeefc0b300393efa18eaf8a0c4403fac7448427d0cb23a48bfe4558654d206b
+size 1836707464

quantize_config.json

@@ -0,0 +1,56 @@
+{
+  "bits": 4,
+  "dataset": [
+    "Human: I had a dream about us last night. It was so real, I woke up smiling.\nAssistant: MSG1: I had a dream about us last night. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It was so real, I woke up smiling. \\| DELAY2: 3 \\| DELAY_REASON2: building intrigue",
+    "Human: I'm at our favorite caf\u00e9 and it feels empty without you here. Missing you.\nAssistant: MSG1: I'm at our favorite caf\u00e9 right now. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It feels empty without you here. Missing you. \\| DELAY2: 4 \\| DELAY_REASON2: expressing feelings",
+    "Human: You won't believe what just happened at work! It's absolutely crazy.\nAssistant: MSG1: You won't believe what just happened at work! \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It's absolutely crazy. \\| DELAY2: 3 \\| DELAY_REASON2: building excitement",
+    "Human: Remember that movie we talked about? Guess what, I got tickets for us!\nAssistant: MSG1: Remember that movie we talked about? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Guess what, I got tickets for us! \\| DELAY2: 4 \\| DELAY_REASON2: revealing a surprise",
+    "Human: Cooking dinner tonight, wish you were here to taste test. \ud83c\udf72\nAssistant: MSG1: Cooking dinner tonight. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Wish you were here to taste test. \ud83c\udf72 \\| DELAY2: 3 \\| DELAY_REASON2: sharing a moment",
+    "Human: Just passed by that bookstore you love. Made me think of you immediately.\nAssistant: MSG1: Just passed by that bookstore you love. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Made me think of you immediately. \\| DELAY2: 4 \\| DELAY_REASON2: conveying affection",
+    "Human: Had a tough day. Really could use one of your hugs right now.\nAssistant: MSG1: Had a tough day. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Really could use one of your hugs right now. \\| DELAY2: 5 \\| DELAY_REASON2: seeking comfort",
+    "Human: You know what? I'm really lucky to have you in my life.\nAssistant: MSG1: You know what? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: I'm really lucky to have you in my life. \\| DELAY2: 3 \\| DELAY_REASON2: expressing gratitude and love",
+    "Human: Watching our show without you just isn't the same. Can't wait to watch it together again.\nAssistant: MSG1: Watching our show without you. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Just isn't the same. Can't wait to watch it together again. \\| DELAY2: 5 \\| DELAY_REASON2: sharing experiences and anticipation",
+    "Human: I was thinking about our last trip, remember that sunset on the beach? It was so beautiful, just like you. It made me realize how much I enjoy our adventures together. Can't wait for our next one.\nAssistant: MSG1: I was thinking about our last trip, remember that sunset on the beach? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: It was so beautiful, just like you. \\| DELAY2: 3 \\| DELAY_REASON2: sharing a memory\nMSG3: It made me realize how much I enjoy our adventures together. \\| DELAY3: 6 \\| DELAY_REASON3: expressing feelings\nMSG4: Can't wait for our next one. \\| DELAY4: 3 \\| DELAY_REASON4: looking forward to future plans",
+    "Human: Just saw a shooting star and made a wish for us.\nAssistant: MSG1: Just saw a shooting star and made a wish for us. \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+    "Human: Your favorite song is playing on the radio, made me smile.\nAssistant: MSG1: Your favorite song is playing on the radio, made me smile. \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+    "Human: Found that book you mentioned, picking it up for you!\nAssistant: MSG1: Found that book you mentioned, picking it up for you! \\| DELAY1: 0 \\| DELAY_REASON1: first message",
+    "Human: Hey, how's your day going? Just finished a meeting, thought of calling you. Let's catch up tonight?\nAssistant: MSG1: Hey, how's your day going? \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Just finished a meeting, thought of calling you. \\| DELAY2: 4 \\| DELAY_REASON2: natural conversation flow\nMSG3: Let's catch up tonight? \\| DELAY3: 5 \\| DELAY_REASON3: proposing a plan",
+    "Human: Woke up missing you more than usual today. What are you up to? Maybe we can meet later.\nAssistant: MSG1: Woke up missing you more than usual today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: What are you up to? \\| DELAY2: 3 \\| DELAY_REASON2: showing interest\nMSG3: Maybe we can meet later. \\| DELAY3: 6 \\| DELAY_REASON3: suggesting a meeting",
+    "Human: Hey, just got back from the gym. Feeling pumped!\nAssistant: MSG1: Hey, just got back from the gym. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling pumped! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+    "Human: I tried making that dish you love for dinner. Nailed it!\nAssistant: MSG1: I tried making that dish you love for dinner. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Nailed it! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Stuck in traffic again. This commute is killing me.\nAssistant: MSG1: Stuck in traffic again. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: This commute is killing me. \\| DELAY2: 4 \\| DELAY_REASON2: expressing frustration",
+    "Human: Just finished reading that book you recommended. Couldn't put it down!\nAssistant: MSG1: Just finished reading that book you recommended. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Couldn't put it down! \\| DELAY2: 3 \\| DELAY_REASON2: sharing enthusiasm",
+    "Human: Missed my morning coffee today. Feeling groggy.\nAssistant: MSG1: Missed my morning coffee today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling groggy. \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+    "Human: Just finished my last exam of the semester. Time to celebrate!\nAssistant: MSG1: Just finished my last exam of the semester. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Time to celebrate! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Ran into an old friend today. Brought back so many memories.\nAssistant: MSG1: Ran into an old friend today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Brought back so many memories. \\| DELAY2: 4 \\| DELAY_REASON2: reminiscing",
+    "Human: Planning a surprise party for your birthday. Can't wait to see your reaction!\nAssistant: MSG1: Planning a surprise party for your birthday. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Can't wait to see your reaction! \\| DELAY2: 4 \\| DELAY_REASON2: anticipating excitement",
+    "Human: Just got promoted at work! Hard work pays off.\nAssistant: MSG1: Just got promoted at work! \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Hard work pays off. \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Feeling stressed out lately. Need a break.\nAssistant: MSG1: Feeling stressed out lately. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Need a break. \\| DELAY2: 3 \\| DELAY_REASON2: expressing need for relaxation",
+    "Human: Just finished my morning workout. Feeling energized!\nAssistant: MSG1: Just finished my morning workout. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling energized! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+    "Human: Finally got around to organizing my closet. Feels so satisfying.\nAssistant: MSG1: Finally got around to organizing my closet. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feels so satisfying. \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Traffic is insane today. Already late for my meeting.\nAssistant: MSG1: Traffic is insane today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Already late for my meeting. \\| DELAY2: 4 \\| DELAY_REASON2: expressing frustration",
+    "Human: Tried a new recipe for lunch. Turned out better than expected!\nAssistant: MSG1: Tried a new recipe for lunch. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Turned out better than expected! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Feeling a bit under the weather today. Need some rest.\nAssistant: MSG1: Feeling a bit under the weather today. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Need some rest. \\| DELAY2: 3 \\| DELAY_REASON2: expressing need for relaxation",
+    "Human: Finished reading a great book last night. Highly recommend it.\nAssistant: MSG1: Finished reading a great book last night. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Highly recommend it. \\| DELAY2: 3 \\| DELAY_REASON2: sharing enthusiasm",
+    "Human: Attended a fascinating lecture this afternoon. Feeling inspired!\nAssistant: MSG1: Attended a fascinating lecture this afternoon. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Feeling inspired! \\| DELAY2: 3 \\| DELAY_REASON2: sharing mood",
+    "Human: Can't believe it's already Friday. Any plans for the weekend?\nAssistant: MSG1: Can't believe it's already Friday. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Any plans for the weekend? \\| DELAY2: 4 \\| DELAY_REASON2: natural conversation flow",
+    "Human: Finished a big project at work. Time to celebrate!\nAssistant: MSG1: Finished a big project at work. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Time to celebrate! \\| DELAY2: 3 \\| DELAY_REASON2: sharing achievement",
+    "Human: Just signed up for a new fitness class. Excited to try it out!\nAssistant: MSG1: Just signed up for a new fitness class. \\| DELAY1: 0 \\| DELAY_REASON1: first message\nMSG2: Excited to try it out! \\| DELAY2: 3 \\| DELAY_REASON2: sharing anticipation"
+  ],
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "use_cuda_fp16": true,
+  "model_seqlen": 4096,
+  "block_name_to_quantize": "model.layers",
+  "module_name_preceding_first_block": [
+    "model.embed_tokens",
+    "model.embed_dropout"
+  ],
+  "batch_size": 1,
+  "pad_token_id": null,
+  "disable_exllama": false,
+  "quant_method": "gptq"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,323 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}