Update README.md

README.md

@@ -1,10 +1,13 @@
 ---
 license: other
+license_name: llama-3
+license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE
+
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - generated_from_trainer
 model-index:
-- name: workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
+- name: lightblue/suzume-llama-3-8B-multilingual
   results: []
 ---
 
@@ -38,9 +41,9 @@ sample_packing: true
 pad_to_sequence_len: true
 
 use_wandb: true
-wandb_project: axolotl
-wandb_entity: peterd
-wandb_name: tagengo_openchat_megagon_8B_instruct
+wandb_project: wandb_project
+wandb_entity: wandb_entity
+wandb_name: wandb_name
 
 gradient_accumulation_steps: 2
 micro_batch_size: 2
@@ -77,23 +80,68 @@ special_tokens:
 
 </details><br>
 
-# workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
+<p align="center">
+  <img width=400 src="https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kg3QjQOde0X743csGJT-f.png" alt="Suzume - a Japanese tree sparrow"/>
+</p>
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6595
+# Suzume
+
+This Suzume 8B, a multilingual finetune of Llama 3.
+
+Llama 3 has exhibited excellent performance on many English language benchmarks. 
+However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in other languages.
 
-## Model description
+We have fine-tuned Llama 3 on almost 90,000 multilingual conversations meaning that this model has the smarts of Llama 3 but has the added ability to chat in more languages.
 
-More information needed
+Please feel free to comment on this model and give us feedback in the Community tab!
 
-## Intended uses & limitations
+# How to use
 
-More information needed
+The easiest way to use this model on your own computer is to use the [GGUF version of this model (lightblue/suzume-llama-3-8B-multilingual-gguf)](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-gguf) using a program such as (jan.ai)[https://jan.ai/] or [LM Studio](https://lmstudio.ai/).
+
+If you want to use this model directly in Python, we recommend using vLLM for the fastest inference speeds.
+
+```python
+from vllm import LLM, SamplingParams
+
+sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
+llm = LLM(model="lightblue/suzume-llama-3-8B-multilingual")
+
+messages = []
+messages.append({"role": "user", "content": "Bonjour!"})
+prompt = llm.llm_engine.tokenizer.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
+prompts = [prompt]
+
+outputs = llm.generate(prompts, sampling_params)
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
 
-## Training and evaluation data
+# Evaluation scores
+
+We achieve the following MT-Bench scores across 6 languages:
+
+
+
+# Training data
+
+We train on three sources of data to create this model:
+
+* [lightblue/tagengo-gpt4](https://huggingface.co/datasets/lightblue/tagengo-gpt4) - 76,338 conversations
+    * A diverse dataset of initial inputs sampled from [lmsys/lmsys-chat-1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) and then used to prompt `gpt-4-0125-preview`
+* [megagonlabs/instruction_ja](https://github.com/megagonlabs/instruction_ja) - 669 conversations
+    * A hand-edited dataset of nearly 700 Japanese conversations taken originally from translations of the [kunishou/hh-rlhf-49k-ja](https://huggingface.co/datasets/kunishou/hh-rlhf-49k-ja) dataset.
+* [openchat/openchat_sharegpt4_dataset](https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/resolve/main/sharegpt_gpt4.json) - 6,206 conversations
+    * Conversations taken from humans talking to GPT-4
+
+# workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the above described dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6595
 
-More information needed
 
 ## Training procedure