add model files

README.md

@@ -1,3 +1,102 @@
----
-license: llama3
----
+---
+library_name: transformers
+tags: []
+base_model:
+  - flammenai/Mahou-1.1-llama3-8B
+datasets:
+  - flammenai/Grill-preprod-v1_chatML
+license: llama3
+---
+
+![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
+
+# Mahou-1.1-llama3-8B
+
+Mahou is our attempt to build a production-ready conversational/roleplay LLM.
+
+Future versions will be released iteratively and finetuned from flammen.ai conversational data.
+
+### 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|>
+```
+
+### ST Settings
+
+1. Use ChatML for the Context Template.
+2. Turn on Instruct Mode for ChatML.
+3. Use the following stopping strings: `["<", "|", "<|", "\n"]`
+
+### License
+
+This model is based on Meta Llama-3-8B and is governed by the [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE).
+
+### Method
+
+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=2,
+    gradient_accumulation_steps=2,
+    gradient_checkpointing=True,
+    learning_rate=3e-5,
+    lr_scheduler_type="cosine",
+    max_steps=420,
+    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
+)
+```

ggml-model-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678a1680ed8048bda38a24259b230a837c669a81a56861ef5ccb96472b678773
+size 4018917600

ggml-model-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9506414a6d0cf1f1c0e8a65742510bb2eedd090c4c3904731b0e309ab35e0cdc
+size 4920733920

ggml-model-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6affd7b9a43295ca2122c6853bfe5be127ab87b53db37ec390dfec70a5d73a9e
+size 5732987104