Create README.md

README.md

@@ -0,0 +1,161 @@
+---
+license: apache-2.0
+language:
+- en
+- de
+- es
+- fr
+- it
+- pt
+- pl
+- nl
+- tr
+- sv
+- cs
+- el
+- hu
+- ro
+- fi
+- uk
+- sl
+- sk
+- da
+- lt
+- lv
+- et
+- bg
+- 'no'
+- ca
+- hr
+- ga
+- mt
+- gl
+- zh
+- ru
+- ko
+- ja
+- ar
+- hi
+library_name: transformers
+base_model:
+- utter-project/EuroLLM-9B-2512
+---
+
+# Model Card for EuroLLM-9B-Instruct-2512
+
+This is the model card for EuroLLM-9B-Instruct-2512, an improved version of [utter-project/EuroLLM-9B-Instruct](https://huggingface.co/utter-project/EuroLLM-9B-Instruct).
+In comparison with the previous version, this version includes the long-context extension phase and the revamped post-training recipe from [utter-project/EuroLLM-22B-Instruct](https://huggingface.co/utter-project/EuroLLM-22B-Instruct-2512).
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.12.2`
+```yaml
+auto_resume_from_checkpoints: true
+use_tensorboard: true
+
+base_model: utter-project/EuroLLM-9B-2512
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+dataset_processes: 64
+datasets:
+  - path: utter-project/EuroBlocks-SFT-2512
+    type: chat_template
+    split: train
+    conversation: chatml
+    field_messages: conversations
+    message_field_role: role
+    message_field_content: content
+    roles_to_train: ["assistant"]
+    train_on_eos: all
+
+
+chat_template_jinja: "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}\n{{ message['content'] | trim }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}"
+ 
+output_dir: checkpoints
+val_set_size: 0
+
+sequence_len: 32768
+sample_packing: true
+pad_to_sequence_len: true
+
+# sequence_parallel_degree: 4
+# heads_k_stride: 1
+# ring_attn_func:
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+
+# N_GPUS * GRAD_ACC_STEPS * MICRO_BATCH_SIZE * SEQ_LEN = tokens/step ->
+# Assuming 32 gpus (32 * 2 * 2 * 32k = 4 096 000 tokens/step)
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+
+eval_batch_size: 1
+num_epochs: 5
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 1e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+logging_steps: 1
+flash_attention: true
+flash_attn_cross_entropy: false
+flash_attn_rms_norm: false
+flash_attn_fuse_qkv: false
+flash_attn_fuse_mlp: false
+
+warmup_steps: 125
+eval_sample_packing: False
+save_steps: 500
+save_total_limit: 2
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.01
+
+special_tokens:
+  eos_token: "<|im_end|>"
+
+```
+</details><br>
+
+## Run the model
+    
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    
+    model_id = "utter-project/EuroLLM-9B-Instruct-2512"
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id)
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are EuroLLM --- an AI assistant specialized in European languages that provides safe, educational and helpful answers.",
+        },
+        {
+            "role": "user", "content": "What is the capital of Portugal? How would you describe it?"
+        },
+        ]
+
+    inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+    outputs = model.generate(inputs, max_new_tokens=1024)
+    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+## Bias, Risks, and Limitations
+
+EuroLLM-9B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).