Update README.md

README.md

@@ -1,11 +1,16 @@
 ---
 library_name: transformers
-tags: []
+datasets:
+- PhilSad/Alpaca_french_instruct_sft
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+(experimental)
+
+This is a 4 bits PEFT QLORA fine tuning of Claire-7b-0.1 on 150 steps on a dataset adapted from tbboukhari/Alpaca_french_instruct.
+The model is in 4bits
+[Training script](https://github.com/PhilSad/claire-instruct/blob/main/train.ipynb)
 
 
 
@@ -17,185 +22,134 @@ tags: []
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
+- **Developed by:** Philippe Saade
+- **Language(s) (NLP):** French
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Finetuned from model:** OpenLLM-France/Claire-7B-0.1
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
+- **Repository:** https://github.com/PhilSad/claire-instruct
 - **Paper [optional]:** [More Information Needed]
 - **Demo [optional]:** [More Information Needed]
 
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```python
+#!pip install transformers accelerate bitsandbytes
+
+import transformers
+import torch
+
+model_name = "PhilSad/Claire-7b-0.1-instruct"
+
+tokenizer = transformers.AutoTokenizer.from_pretrained("OpenLLM-France/Claire-7B-0.1")
+model_instruct = transformers.AutoModelForCausalLM.from_pretrained(model_name,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
+
+pipeline_instruct = transformers.pipeline("text-generation", model=model_instruct, tokenizer=tokenizer)
+generation_kwargs = dict(
+    num_return_sequences=1,                    # Number of variants to generate.
+    return_full_text= False,                   # Do not include the prompt in the generated text.
+    max_new_tokens=200,                        # Maximum length for the output text.
+    do_sample=True, top_k=10, temperature=1.0, # Sampling parameters.
+    pad_token_id=tokenizer.eos_token_id,       # Just to avoid a harmless warning.
+)
+
+prompt = """Ci-dessous se trouve une instruction qui décrit une tâche. Écrivez une réponse qui complète de manière appropriée la demande.
+
+### Instruction :
+Donne moi la recette pour faire un bon mojito
+
+### Réponse :"""
+completions = pipeline_instruct(prompt, **generation_kwargs)
+for completion in completions:
+    print(prompt + " […]" + completion['generated_text'])
+```
+<details>
+<summary>Output instruct</summary>
+```
+Le mojito est un cocktail alcoolisé originaire des Antilles, et c'est maintenant l'un des cocktails les plus appréciés. Les ingrédients du mojito comprennent du citron vert, du sirop de sucre, de l'eau gazeuse, de la menthe fraîche et de l'épeautre. La première étape pour faire un bon cocktail Mojito est de couper le citron vert en fines rondelles avec un couteau. Vous devez ensuite frotter le bord de votre verre avec le citron vert, et le mettre avec vos autres ingrédients. Vous devez ensuite verser de l'eau gazeuse dans le verre, et le faire glisser. Pour finir, vous devez mettre les feuilles de menthe fraîche et les bâtonnets de sucre dans le verre, et servir la boisson à vos invités! Bonne chance et bonne dégust
+```
+</details>
+<details>
+<summary>Output claire base</summary>
+```
+- Donnez moi la recette pour faire un bon mojito
+- Un bon mojito, euh je dirais qu'il faut un citron, des feuilles de menthe, de l'eau gazeuse euh et puis euh des glaçons. Et puis euh des glaçons.
+- Et qu'est-ce que qu'est-ce que...
+- Euh et puis euh...
+- Qu'est-ce que c'est qu'est-ce que...
+- Quoi?
+- Tu peux dire ce que tu penses. Qu'est-ce que tu penses? Est-ce que c'est une bonne recette?
+- Ouais.
+- Est-ce que c'est la bonne recette?
+- Oui je pense mais je sais qu'il y a pas beaucoup de gens qui la connaissent en fait.
+- D'accord.
+- Et puis euh...
+- Et est-ce que c'est une bonne recette?
+- Oui je pense. Je sais qu'il y a pas beaucoup de gens qui la connaissent en fait. Et puis euh...
+- Est-ce que c'est une bonne recette?
+- Oui je pense mais je sais qu'il y a pas beaucoup de gens qui la connaissent en fait.
+- Oui.
+- Et puis e
+```
+</details>
 
-## Training Details
 
-### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+## Training Details
 
-[More Information Needed]
 
 ### Training Procedure 
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+I used this [guide](https://wandb.ai/capecape/alpaca_ft/reports/How-to-Fine-tune-an-LLM-Part-3-The-HuggingFace-Trainer--Vmlldzo1OTEyNjMy)
 
-#### Preprocessing [optional]
-
-[More Information Needed]
-
+[Training script](https://github.com/PhilSad/claire-instruct/blob/main/train.ipynb)
 
 #### Training Hyperparameters
 
 - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+4 bits
+
+per_device_train_batch_size = 4 #4
+gradient_accumulation_steps = 4
+optim = "paged_adamw_32bit"
+learning_rate = 2e-4
+max_grad_norm = 0.3
+max_steps = 300 #100 #500
+warmup_ratio = 0.03
+lr_scheduler_type = "cosine"
+
+
+lora_alpha = 32 #16
+lora_dropout = 0.05 #0.1
+lora_rank = 32 #64
+
+peft_config = LoraConfig(
+    lora_alpha=lora_alpha,
+    lora_dropout=lora_dropout,
+    r=lora_rank,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=[
+        "query_key_value",
+        "dense",
+        "dense_h_to_4h",
+        "dense_4h_to_h",
+    ]
+)
 
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
 
-## Model Card Contact
 
-[More Information Needed]