Upload LlamaForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID
@@ -11,86 +13,189 @@ tags: []
 
 ## Model Details
 
-{
-    "eval_AVGf1": 0.9223289834840258,
-    "eval_accuracy": 0.9272914758360438,
-    "eval_diagnosis.avg_words_per_entity": 2.2245762711864407,
-    "eval_diagnosis.entity_count": 2360,
-    "eval_diagnosis.f1": 0.8788986878898688,
-    "eval_diagnosis.precision": 0.8925294888597641,
-    "eval_diagnosis.recall": 0.8656779661016949,
-    "eval_diagnosis.word_count": 5250,
-    "eval_diagnostic.avg_words_per_entity": 1.8057921635434413,
-    "eval_diagnostic.entity_count": 1761,
-    "eval_diagnostic.f1": 0.9564464955292761,
-    "eval_diagnostic.precision": 0.9718640093786636,
-    "eval_diagnostic.recall": 0.9415105053946621,
-    "eval_diagnostic.word_count": 3180,
-    "eval_drug.avg_words_per_entity": 1.0905096660808435,
-    "eval_drug.entity_count": 1138,
-    "eval_drug.f1": 0.957187922487607,
-    "eval_drug.precision": 0.9824236817761333,
-    "eval_drug.recall": 0.9332161687170475,
-    "eval_drug.word_count": 1241,
-    "eval_f1": 0.6559352257940142,
-    "eval_loss": 0.005444246344268322,
-    "eval_medical_finding.avg_words_per_entity": 4.152033985581874,
-    "eval_medical_finding.entity_count": 7768,
-    "eval_medical_finding.f1": 0.9184775620419185,
-    "eval_medical_finding.precision": 0.917415874646802,
-    "eval_medical_finding.recall": 0.9195417095777549,
-    "eval_medical_finding.word_count": 32253,
-    "eval_model_preparation_time": 0.0,
-    "eval_precision": 0.5121161950632149,
-    "eval_recall": 0.9120761292052004,
-    "eval_runtime": 311.6758,
-    "eval_samples_per_second": 26.252,
-    "eval_steps_per_second": 6.565,
-    "eval_therapy.avg_words_per_entity": 3.6986807387862797,
-    "eval_therapy.entity_count": 1895,
-    "eval_therapy.f1": 0.9006342494714588,
-    "eval_therapy.precision": 0.9020645844362096,
-    "eval_therapy.recall": 0.8992084432717679,
-    "eval_therapy.word_count": 7009,
-    
-    "test_AVGf1": 0.8991844061835648,
-    "test_accuracy": 0.9393252816821795,
-    "test_diagnosis.avg_words_per_entity": 2.540414878397711,
-    "test_diagnosis.entity_count": 2796,
-    "test_diagnosis.f1": 0.7905454545454544,
-    "test_diagnosis.precision": 0.8039940828402367,
-    "test_diagnosis.recall": 0.7775393419170243,
-    "test_diagnosis.word_count": 7103,
-    "test_diagnostic.avg_words_per_entity": 1.9772727272727273,
-    "test_diagnostic.entity_count": 2156,
-    "test_diagnostic.f1": 0.9380572501173158,
-    "test_diagnostic.precision": 0.9491927825261158,
-    "test_diagnostic.recall": 0.9271799628942486,
-    "test_diagnostic.word_count": 4263,
-    "test_drug.avg_words_per_entity": 1.033793103448276,
-    "test_drug.entity_count": 1450,
-    "test_drug.f1": 0.9711267605633803,
-    "test_drug.precision": 0.9920863309352518,
-    "test_drug.recall": 0.9510344827586207,
-    "test_drug.word_count": 1499,
-    "test_f1": 0.6601992430504198,
-    "test_loss": 0.005932590924203396,
-    "test_medical_finding.avg_words_per_entity": 4.681758451797873,
-    "test_medical_finding.entity_count": 8371,
-    "test_medical_finding.f1": 0.900312076782665,
-    "test_medical_finding.precision": 0.8877148165350673,
-    "test_medical_finding.recall": 0.9132720105124835,
-    "test_medical_finding.word_count": 39191,
-    "test_model_preparation_time": 0.0,
-    "test_precision": 0.5235630994273097,
-    "test_recall": 0.8933364728043325,
-    "test_runtime": 357.9554,
-    "test_samples_per_second": 26.509,
-    "test_steps_per_second": 6.629,
-    "test_therapy.avg_words_per_entity": 3.9787810383747177,
-    "test_therapy.entity_count": 2215,
-    "test_therapy.f1": 0.8958804889090086,
-    "test_therapy.precision": 0.8983204720835225,
-    "test_therapy.recall": 0.8934537246049662,
-    "test_therapy.word_count": 8813
-}
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+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]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### 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. -->
+
+[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]
+
+## 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. -->
+
+[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. -->
+
+### 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]

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/jovyan/work/Ca-Test/Ca-lower_labels_r100_O2_f100_LT/checkpoint-511",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72476060470339037f9ed4f9c7ea31f15e1e7a88217ac71e48f542a11d443265
+size 4400232920