Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+Mahou-1.2b-mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mahou-1.2b-mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mahou-1.2b-mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mahou-1.2b-mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Mahou-1.2b-mistral-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875c043a6f6d57feee1db755a123c609d758261bb3f78b5585ecce509d4b55c6
+size 3518986240

Mahou-1.2b-mistral-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b94e84852db5f9be9fbb1393d4e2451e8ea5744527f527da8ac0f12f86d4b5
+size 4368439296

Mahou-1.2b-mistral-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f3a16a22eb2a650b9f9daee80e38fcb92a2ac53a58c7ceed4eb56f1929992d
+size 5131409408

Mahou-1.2b-mistral-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a98f2f464645016848d3f923609fe428b9862899040fb1a2e1e23cbbd29f22
+size 7695857664

README.md

@@ -0,0 +1,107 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model:
+- nbeerbower/Mahou-1.2a-mistral-7B
+datasets:
+- flammenai/MahouMix-v1
+- flammenai/FlameMix-DPO-v1
+---
+![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
+
+# Mahou-1.2b-mistral-7B
+
+Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.
+
+### Chat Format
+
+This model has been trained to use ChatML format.
+
+```
+<|im_start|>system
+{{system}}<|im_end|>
+<|im_start|>{{char}}
+{{message}}<|im_end|>
+<|im_start|>{{user}}
+{{message}}<|im_end|>
+```
+
+### Roleplay Format
+
+- Speech without quotes.
+- Actions in `*asterisks*`
+
+```
+*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.
+```
+
+### SillyTavern Settings
+
+1. Use ChatML for the Context Template.
+2. Enable Instruct Mode.
+3. Use the [Mahou preset](https://huggingface.co/datasets/flammenai/Mahou-ST-ChatML-Instruct/raw/main/Mahou.json).
+4. *Recommended* Additonal stopping strings: `["\n", "<|", "</"]`
+
+### Method
+
+DPO finetuned using an A100 on Google Colab.
+
+[Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)
+
+### Configuration
+
+LoRA, model, and training settings:
+
+```python
+# LoRA configuration
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=16,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
+)
+# Model to fine-tune
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    load_in_4bit=True
+)
+model.config.use_cache = False
+# Reference model
+ref_model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    load_in_4bit=True
+)
+# Training arguments
+training_args = TrainingArguments(
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    gradient_checkpointing=True,
+    learning_rate=5e-5,
+    lr_scheduler_type="cosine",
+    max_steps=2000,
+    save_strategy="no",
+    logging_steps=1,
+    output_dir=new_model,
+    optim="paged_adamw_32bit",
+    warmup_steps=100,
+    bf16=True,
+    report_to="wandb",
+)
+# Create DPO trainer
+dpo_trainer = DPOTrainer(
+    model,
+    ref_model,
+    args=training_args,
+    train_dataset=dataset,
+    tokenizer=tokenizer,
+    peft_config=peft_config,
+    beta=0.1,
+    force_use_ref_model=True
+)
+# Fine-tune model with DPO
+dpo_trainer.train()
+```