Training in progress, step 20

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+base_model: unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit
+library_name: transformers
+model_name: unsloth-mistral-wine-sft
+tags:
+- generated_from_trainer
+- trl
+- sft
+- unsloth
+licence: license
+---
+
+# Model Card for unsloth-mistral-wine-sft
+
+This model is a fine-tuned version of [unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="anna-tch/unsloth-mistral-wine-sft", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ddac531063de23ae584523bc04df34761d7ed3a84efaa12b2b7669378d6a6b
+size 629189608

chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}

runs/May28_10-41-18_r-anna-tch-jupyterlab-aktar35p-71277-lc9rc/events.out.tfevents.1779957678.r-anna-tch-jupyterlab-aktar35p-71277-lc9rc.6756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160e8fb07233be6ae6b4a330f0b914a6478a64137497cb8b0dac0adae014a36c
+size 6317

runs/May28_10-49-42_r-anna-tch-jupyterlab-aktar35p-71277-lc9rc/events.out.tfevents.1779958182.r-anna-tch-jupyterlab-aktar35p-71277-lc9rc.6756.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f051da7518f12d6e315b32c3ce1ca51242622cc95f3ca8b083a510c75e43b96
+size 10473

runs/May28_11-18-33_r-anna-tch-jupyterlab-aktar35p-71277-lc9rc/events.out.tfevents.1779959913.r-anna-tch-jupyterlab-aktar35p-71277-lc9rc.17611.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931fa9fcba136a88ac33e27f727b54d2f0eaa57817263a091ac5b235482f270b
+size 6200

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e7dacefab0eac2483f25060204a445e367f24533f12bfb673cdf30d3b67c3c
+size 5905