Upload folder using huggingface_hub

Everything-LM/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a991d74cf01bc5993d7d515e6c91abb9aacf2250cc5e32c7912ed38e3764b1d
+size 80114765

Everything-LM/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

Everything-LM/checkpoint-2/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a04a5ca22abdae32458bd108cafa031afc19b36fd26be501f6a79361c29dc8c
+size 80114765

Everything-LM/checkpoint-2/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-2/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-2/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a04a5ca22abdae32458bd108cafa031afc19b36fd26be501f6a79361c29dc8c
+size 80114765

Everything-LM/checkpoint-2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3318079d84860039de45c144aa3fe2e9d0e56190bfc36e1c2b9e412d0598ee26
+size 40569887

Everything-LM/checkpoint-2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984433fd7be740b2d6360cfe44e349d5a40ecb2285791768d183ed3afcfc48aa
+size 14575

Everything-LM/checkpoint-2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69965cd123fba88348bcf5858148ecb2990698e61613f3f725965ea841e49de
+size 627

Everything-LM/checkpoint-2/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8648648648648649,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.5099,
+      "step": 1
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000225,
+      "loss": 1.4484,
+      "step": 2
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 6,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.2089671264763904e+16,
+  "trial_name": null,
+  "trial_params": null
+}

Everything-LM/checkpoint-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5069800a33ca54bf43c3b93e1d5f640909151ea51562afd2230d8c868d36ff7b
+size 4155

Everything-LM/checkpoint-4/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-4/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-4/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9fe4007d8a741162ca6333b04b5e5df236fc4c410a30f8bde31fbda5ea0b4c
+size 80114765

Everything-LM/checkpoint-4/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-4/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-4/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9fe4007d8a741162ca6333b04b5e5df236fc4c410a30f8bde31fbda5ea0b4c
+size 80114765

Everything-LM/checkpoint-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5487ddde84775df62200352f01ec1c66a2cb3960ede96aadbd22f95022927fc
+size 40569887

Everything-LM/checkpoint-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b85a7a337110f6a2d8109bdab3eec70d3e60c4e6b04e854ff5998d9e8f9f68
+size 14575

Everything-LM/checkpoint-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60fa183fd6ae9404348042f9312b80e0a1fb1bc4a4feda8a143c9f9c99975d7
+size 627

Everything-LM/checkpoint-4/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7297297297297298,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.5099,
+      "step": 1
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000225,
+      "loss": 1.4484,
+      "step": 2
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00015,
+      "loss": 1.4938,
+      "step": 3
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 1.4088,
+      "step": 4
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 6,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.4157216960413696e+16,
+  "trial_name": null,
+  "trial_params": null
+}

Everything-LM/checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5069800a33ca54bf43c3b93e1d5f640909151ea51562afd2230d8c868d36ff7b
+size 4155

Everything-LM/checkpoint-6/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-6/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-6/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a991d74cf01bc5993d7d515e6c91abb9aacf2250cc5e32c7912ed38e3764b1d
+size 80114765

Everything-LM/checkpoint-6/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Everything-LM/checkpoint-6/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Everything-LM/checkpoint-6/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a991d74cf01bc5993d7d515e6c91abb9aacf2250cc5e32c7912ed38e3764b1d
+size 80114765

Everything-LM/checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6418f6ca59834adfc8c6238036b82d86a4f38a81210582f84a5693e45c8120
+size 40569887

Everything-LM/checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ad21499347281d1b140497be2595dba5d75ce73b57d40d135e0fdd20c3f4c5
+size 14575

Everything-LM/checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2141b0f152d878006263e11b37207f4c1e1d4252b202dbe2b127e504173c88
+size 627

Everything-LM/checkpoint-6/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5945945945945947,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002799038105676658,
+      "loss": 1.5099,
+      "step": 1
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000225,
+      "loss": 1.4484,
+      "step": 2
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00015,
+      "loss": 1.4938,
+      "step": 3
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 1.4088,
+      "step": 4
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.009618943233419e-05,
+      "loss": 1.3926,
+      "step": 5
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.0,
+      "loss": 1.4358,
+      "step": 6
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 6,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.134282090623795e+16,
+  "trial_name": null,
+  "trial_params": null
+}

Everything-LM/checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5069800a33ca54bf43c3b93e1d5f640909151ea51562afd2230d8c868d36ff7b
+size 4155

Everything-LM/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

Everything-LM/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

Everything-LM/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

Puffin-7B/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Puffin-7B/Untitled.ipynb

@@ -0,0 +1,125 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "670a4958-8306-4a10-a51c-01eb2764f6fe",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "009ab51eb1164706bca69f75874d064e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.bin:   0%|          | 0.00/80.1M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "aed7b179e3eb4de3bd96ba9f4a9b1fbc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Upload 3 LFS files:   0%|          | 0/3 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cd685e7e249c45f891e0ea4f8457288b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.bin:   0%|          | 0.00/80.1M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b2293c2c58b0435f849a8d79087972c2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "optimizer.pt:   0%|          | 0.00/40.6M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/datasets/nRuaif/temp/tree/main/'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from huggingface_hub import HfApi\n",
+    "\n",
+    "api = HfApi()\n",
+    "\n",
+    "# Upload all the content from the local folder to your remote Space.\n",
+    "# By default, files are uploaded at the root of the repo\n",
+    "\n",
+    "api.upload_folder(\n",
+    "\n",
+    "    folder_path=\"/workspace/axolotl\",\n",
+    "\n",
+    "    repo_id=\"nRuaif/temp\",\n",
+    "\n",
+    "    repo_type=\"dataset\",\n",
+    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88e74658-49b3-4c3b-a2a2-2ba7225cb3e1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Puffin-7B/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Puffin-7B/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

Puffin-7B/checkpoint-20/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Puffin-7B/checkpoint-20/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Puffin-7B/checkpoint-20/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21e5f4dcceb76ea3181f0c5f052515f8d8733911db0785eb6c7ae5e10a7e796
+size 80114765

Puffin-7B/checkpoint-20/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

Puffin-7B/checkpoint-20/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Puffin-7B/checkpoint-20/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21e5f4dcceb76ea3181f0c5f052515f8d8733911db0785eb6c7ae5e10a7e796
+size 80114765