Upload 108 files

.gitattributes

@@ -33,3 +33,88 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/0 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/1 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/10 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/100 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/102 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/104 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/105 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/106 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/107 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/108 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/109 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/11 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/110 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/111 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/112 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/113 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/114 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/116 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/118 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/119 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/12 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/120 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/121 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/122 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/123 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/124 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/125 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/126 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/127 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/128 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/13 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/130 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/132 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/133 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/134 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/135 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/136 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/137 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/138 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/139 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/14 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/140 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/141 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/142 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/144 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/146 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/147 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/148 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/149 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/15 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/150 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/151 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/152 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/153 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/154 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/155 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/156 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/158 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/16 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/160 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/161 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/162 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/163 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/164 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/165 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/166 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/167 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/168 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/169 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/170 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/172 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/174 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/175 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/176 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/177 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/178 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/179 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/18 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/180 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/181 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/182 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/183 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/184 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/186 filter=lfs diff=lfs merge=lfs -text
+adapter_model/data/188 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,88 +1,73 @@
 ---
 license: apache-2.0
-pipeline_tag: text-generation
+library_name: peft
 tags:
-- finetuned
-inference: true
-widget:
-- messages:
-  - role: user
-    content: What is your favorite condiment?
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: tmp/helix/results/e9624262-34ea-4818-a31f-84692d26fc66
+  results: []
 ---
 
-# Model Card for Mistral-7B-Instruct-v0.2
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# tmp/helix/results/e9624262-34ea-4818-a31f-84692d26fc66
 
-Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
-- 32k context window (vs 8k context in v0.1)
-- Rope-theta = 1e6
-- No Sliding-Window Attention
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
 
-For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).
+## Model description
 
-## Instruction format
+More information needed
 
-In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
+## Intended uses & limitations
 
-E.g.
-```
-text = "<s>[INST] What is your favourite condiment? [/INST]"
-"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
-"[INST] Do you have mayonnaise recipes? [/INST]"
-```
+More information needed
 
-This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
+## Training and evaluation data
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+More information needed
 
-device = "cuda" # the device to load the model onto
+## Training procedure
 
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+### Training hyperparameters
 
-messages = [
-    {"role": "user", "content": "What is your favourite condiment?"},
-    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
-    {"role": "user", "content": "Do you have mayonnaise recipes?"}
-]
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 6
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 20
 
-encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+### Training results
 
-model_inputs = encodeds.to(device)
-model.to(device)
 
-generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
-decoded = tokenizer.batch_decode(generated_ids)
-print(decoded[0])
-```
 
-## Troubleshooting
-- If you see the following error:
-```
-Traceback (most recent call last):
-File "", line 1, in
-File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
-config, kwargs = AutoConfig.from_pretrained(
-File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
-config_class = CONFIG_MAPPING[config_dict["model_type"]]
-File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
-raise KeyError(key)
-KeyError: 'mistral'
-```
+### Framework versions
 
-Installing transformers from source should solve the issue
-pip install git+https://github.com/huggingface/transformers
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0
+## Training procedure
 
-This should not be required after transformers-v4.33.4.
 
-## Limitations
+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
 
-The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. 
-It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
-make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
+### Framework versions
 
-## The Mistral AI Team
 
-Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
+- PEFT 0.6.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model/data.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf47cb5e4b7325d67046dac755b69313f950d1edbaea9e6db1354488b908ee5
+size 73431

adapter_model/data/0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7df746ef25c0c9c759f3a49943a66497d2a0bba1ad8eb3e297e7d3306a5f5f
+size 1048576

adapter_model/data/1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c470ee5883cb1ff46d5243018a03298a274705fe3c4a1e1905de92f77707e37
+size 1048576

adapter_model/data/10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b074949f01ee2cbdf75b672a64a4d3deb719dd0a13e8df9903f71bbe448e90f
+size 1048576

adapter_model/data/100

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef739d9dfab61b8ef773921023f588570acc64b1899647cbc2b23d80bf7047c
+size 1048576

adapter_model/data/102

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1015ce84885054db91ffe1ee8765d87b014cf238ae6b41e2e20702e0de2c93d1
+size 1048576

adapter_model/data/104

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cf879238c8be93f4179893e22a9f0585909885b4240fa356a728de1d4e8611
+size 1048576

adapter_model/data/105

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e39233da79fc1ea4fd6ccdb5c2567b9773350ea20657a1e9f7b48c2a56f3a58
+size 1048576

adapter_model/data/106

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60d0fd8a2be97c22285b0868bcf418459432a07205697ac3237c0b1c11cacd9
+size 1048576

adapter_model/data/107

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9b629c1a36897b927c55ba61cb459988e70b8137277817ef61606d4ad8f1e2
+size 3670016

adapter_model/data/108

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde3c484b8a5f028fd0617a7cc0d5928b30a89ca27ea4159b937a1e8369e385f
+size 1048576

adapter_model/data/109

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0fc07ce979f2961318f06036b9eca74e233c3627a22ee665392a20ae92413b
+size 3670016

adapter_model/data/11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99f185320ae78fd106c94bd66d7987b3c3e07a39cadd27e46cce65fc03177e8
+size 3670016

adapter_model/data/110

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2f097c15531a592295367efdc731dba34cdde45a6c95fef249e7af3e735474
+size 3670016

adapter_model/data/111

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe88a01025078d699e34a15d2d8e4b52e99e450302d5d21267964ea4389db110
+size 1048576

adapter_model/data/112

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0687c1cf9d1d74f1bdf3218589f2b495c18d310b5ac90750ed3a28d0cd8fe0
+size 1048576

adapter_model/data/113

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1530a8091101db44428f5f299ac1356b9cd58f90335f5c82b652eb9b91ba24cb
+size 1048576

adapter_model/data/114

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98d58df46a64b44c0e3de0ba2968063aa96f4986a0c4bc80ac7a611b801325c
+size 1048576

adapter_model/data/116

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0232325393bcba6091866d054ebd207c4de3e49d4b789d909506e4d40390c85
+size 1048576

adapter_model/data/118

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26babfa3397adb5f6b5e9904eac8ff4fe75794bd3b5a156699885f877360b2b
+size 1048576

adapter_model/data/119

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ccd3d06fc9d2b302fea1cb66bc008445c73f292bff0666a8fc8bbae9c37aa6
+size 1048576

adapter_model/data/12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbe89a80a067d5d74f76528bf4facad715feee84921fb7162773081a6e7f4c4
+size 3670016

adapter_model/data/120

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02167c662eee07b96ad0065e78a78dc5218a2cbcbfd1f5a3b9af4efcf3bf4b0c
+size 1048576

adapter_model/data/121

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639a96986b34544cf99ceb5f321c496e2b60993e3af8cceac53d9efe0fd84790
+size 3670016

adapter_model/data/122

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5691485b62978b81fca9c61bf396b3690d25351d6db8e5a2ba12fa3c044041
+size 1048576

adapter_model/data/123

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750221a6dcac81ba35d82f8a9b47be109ea8bd9d4cd180bca71c66500846bff4
+size 3670016

adapter_model/data/124

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd5b0d2e4b1f646a4f30824e2f261fe15fb71c3e9df75161f0c06ae1ca63938
+size 3670016

adapter_model/data/125

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6174f43750eee873ee11f8fc104604aff0495de513cb048b282f0f8843abd8c
+size 1048576

adapter_model/data/126

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a1da69f2dc13802c53a834ba286658342615172e76cee2ba63ae2a764c70ba
+size 1048576

adapter_model/data/127

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc950cc995fa9c4cc9990be58b050859d1f44894c0b54a03d6b2cafa9af7fb16
+size 1048576

adapter_model/data/128

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9b701881b87ef64059387805833e73b88e7c0daf75247d80de1b0bc0f6b1ac
+size 1048576

adapter_model/data/13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95e69ab7613d350207320969fcb45724ac752d440923d9ac0e2d579ca8635d8
+size 1048576

adapter_model/data/130

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0732ae6e14a1243decd1c1c9ef24e602620aac42a0febe9fc8729b3513cf666e
+size 1048576

adapter_model/data/132

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce654fbb2a5be5dae643a4545c346a5350c1ccc79ce0ea14198a1920823dfd4
+size 1048576

adapter_model/data/133

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fc616dd6509b602c58115ebf6f337f63f7c1d4ccf0984b11e202b2101af038
+size 1048576

adapter_model/data/134

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebba6a220990a02e9369ded0ed4e618f67ca5e0827a3fde37cb283ed7fe827a
+size 1048576

adapter_model/data/135

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcd0da8df1fdd77ab2296c0488f14be26693054a01b0cdc564845f1d7ed37fc
+size 3670016

adapter_model/data/136

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb4cee44aff953e18bffd1423ab64eb71abf9fc2607874288a901a55f644f07
+size 1048576

adapter_model/data/137

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf60d7e9527c48ec14b842ae6a81e762de33059ed50d4b7d09205e530bf3f1b
+size 3670016

adapter_model/data/138

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c756fe4428e006e9e2e5a9c8fc41507386e40c097ac9d25a4382947807f7636
+size 3670016

adapter_model/data/139

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c934a665ca4109351af0b3bfeacd4918b7ea87385ce84be972cc36e50f53ea
+size 1048576