Upload folder using huggingface_hub

README.md

@@ -1,113 +1,219 @@
-# Model Card for segmed/MedMistral-7B
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
 
-Medmistral is a language model designed to answer medical questions. It is a qlora fine tune of Mistral-7B-v0.1 that was fine-tuned on the medmcqa dataset.
+# Model Card for Model ID
 
-- **Developed by:** Segmed
-- **Model type:** LLM
+<!-- Provide a quick summary of what the model is/does. -->
 
-### Model Sources https://huggingface.co/mistralai/Mistral-7B-v0.1
 
-## 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. -->
+## Model Details
+
+### Model Description
 
-Prompts were generated using the following:
-```
-def generate_question(data_point):
-    question = f""" {data_point['question']} [0] {data_point['opa']} [1] {data_point['opb']} [2] {data_point['opc']} [3] {data_point['opd']}
-    """
-    return question
+<!-- Provide a longer summary of what this model is. -->
 
-def generate_prompt(data_point):
-    full_prompt=f"""You are a helpful medical assistant. Your task is to answer the following question one of the options and explain why.\n### Question: {generate_question(data_point)}\n### Answer: """
 
-    if data_point["cop"] != "" and data_point["exp"] != "":
-        full_prompt= full_prompt + f"""{data_point["cop"]}\n### Explanation: {data_point["exp"]}"""
 
-    return full_prompt
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
 
-generate_prompt(eval_dataset[random.randrange(len(eval_dataset))])
-```
-Such that the resulting prompt would look like:
-```
-You are a helpful medical assistant. Your task is to answer the following question one of the options and explain why.
-### Question:  "Genital elephantiasis" is seen in: [0] Rickettsia [1] Chancroid [2] Lymphogranuloma venereum [3] Syphilis
-    
-### Answer: 2
-### Explanation: Ans. is. 'c' i. e., Lymphogranuloma venereum
-```
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **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. -->
 
-Below is the code tokenizer, model and helper function to generate new tokens:
-```
-tokenizer_id = "segmed/MedMistral-7B"
-tokenizer = AutoTokenizer.from_pretrained(
-    tokenizer_id,
-    padding_side="left",
-    # model_max_length=4096,
-    add_eos_token=True)
-
-tokenizer.pad_token = tokenizer.eos_token
-
-def tokenize(prompt):
-    result = tokenizer(
-        prompt,
-        truncation=True,
-        padding="max_length",
-        max_length=512,
-    )
-    result["labels"] = result["input_ids"].copy()
-    return result
-
-def tokenize_prompt(data_point):
-    full_prompt = generate_prompt(data_point)
-    return tokenize(full_prompt)
-
-model_id = "segmed/MedMistral-7B"
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
-
-model = AutoModelForCausalLM.from_pretrained(
-    base_model_id,  
-    quantization_config=bnb_config,  # Same quantization config as before
-    device_map="auto",
-    trust_remote_code=True,
-)
-
-def generate_tokens(prompt, max_new_tokens=32):
-    model_input = tokenizer(prompt, return_tensors="pt").to("cuda")
-    model.eval()
-    with torch.no_grad():
-        return tokenizer.decode(model.generate(**model_input, max_new_tokens=max_new_tokens, do_sample=True, top_k=0, num_return_sequences=1, temperature=0.1, eos_token_id=tokenizer.eos_token_id)[0])
-```
+[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. -->
 
-This is not intended for medical advice. We would recommend further testing.
+[More Information Needed]
 
-## Training Details
+### Recommendations
 
-Training occured over the course of 24 hours. 2 epochs were completed on a single A100.
+<!-- 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]
+
+## Training Details
 
 ### Training Data
 
 <!-- This should link to a Data 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. -->
 
-The medmcqa dataset has 193k samples, ~1k of which was used for test and ~1k for eval. This dataset was selected for its quantity of samples as well as multiple choice format for simple evaluation.
+[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. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### 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 -->
+
+#### 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. -->
 
-This dataset was choosen for the simplicty of evaluating. While the prompt asks for an explanation, the actually accuracy can be computed based on the multiple choice output. The results for the evaluation are coming soon.
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
 
+- PEFT 0.7.0.dev0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "lm_head",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd345513ae3e923077e4a1bc5691e45c3cbbcfe836b96825b06f36004a60aa97
+size 170142632