edsl 0.1.39.dev2__py3-none-any.whl → 0.1.39.dev4__py3-none-any.whl

edsl/surveys/Survey.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 import re
+import random
 
 from typing import (
     Any,
@@ -115,6 +116,7 @@ class Survey(SurveyExportMixin, Base):
         rule_collection: Optional["RuleCollection"] = None,
         question_groups: Optional["QuestionGroupType"] = None,
         name: Optional[str] = None,
+        questions_to_randomize: Optional[List[str]] = None,
     ):
         """Create a new survey.
 
@@ -163,6 +165,33 @@ class Survey(SurveyExportMixin, Base):
 
             warnings.warn("name parameter to a survey is deprecated.")
 
+        if questions_to_randomize is not None:
+            self.questions_to_randomize = questions_to_randomize
+        else:
+            self.questions_to_randomize = []
+
+        self._seed = None
+
+    def draw(self) -> "Survey":
+        """Return a new survey with a randomly selected permutation of the options."""
+        if self._seed is None:  # only set once
+            self._seed = hash(self)
+            random.seed(self._seed)
+
+        if len(self.questions_to_randomize) == 0:
+            return self
+
+        new_questions = []
+        for question in self.questions:
+            if question.question_name in self.questions_to_randomize:
+                new_questions.append(question.draw())
+            else:
+                new_questions.append(question.duplicate())
+
+        d = self.to_dict()
+        d["questions"] = [q.to_dict() for q in new_questions]
+        return Survey.from_dict(d)
+
     def _process_raw_questions(self, questions: Optional[List["QuestionType"]]) -> list:
         """Process the raw questions passed to the survey."""
         handler = InstructionHandler(self)
@@ -316,7 +345,9 @@ class Survey(SurveyExportMixin, Base):
         >>> s.to_dict(add_edsl_version = False).keys()
         dict_keys(['questions', 'memory_plan', 'rule_collection', 'question_groups'])
         """
-        return {
+        from edsl import __version__
+
+        d = {
             "questions": [
                 q.to_dict(add_edsl_version=add_edsl_version)
                 for q in self._recombined_questions_and_instructions()
@@ -327,6 +358,13 @@ class Survey(SurveyExportMixin, Base):
             ),
             "question_groups": self.question_groups,
         }
+        if self.questions_to_randomize != []:
+            d["questions_to_randomize"] = self.questions_to_randomize
+
+        if add_edsl_version:
+            d["edsl_version"] = __version__
+            d["edsl_class_name"] = "Survey"
+        return d
 
     @classmethod
     @remove_edsl_version
@@ -370,11 +408,16 @@ class Survey(SurveyExportMixin, Base):
             get_class(q_dict).from_dict(q_dict) for q_dict in data["questions"]
         ]
         memory_plan = MemoryPlan.from_dict(data["memory_plan"])
+        if "questions_to_randomize" in data:
+            questions_to_randomize = data["questions_to_randomize"]
+        else:
+            questions_to_randomize = None
         survey = cls(
             questions=questions,
             memory_plan=memory_plan,
             rule_collection=RuleCollection.from_dict(data["rule_collection"]),
             question_groups=data["question_groups"],
+            questions_to_randomize=questions_to_randomize,
         )
         return survey
 
@@ -870,6 +913,7 @@ class Survey(SurveyExportMixin, Base):
         agent: Optional["Agent"] = None,
         cache: Optional["Cache"] = None,
         disable_remote_inference: bool = False,
+        disable_remote_cache: bool = False,
         **kwargs,
     ):
         """Run the survey with default model, taking the required survey as arguments.
@@ -879,7 +923,7 @@ class Survey(SurveyExportMixin, Base):
         >>> def f(scenario, agent_traits): return "yes" if scenario["period"] == "morning" else "no"
         >>> q = QuestionFunctional(question_name = "q0", func = f)
         >>> s = Survey([q])
-        >>> async def test_run_async(): result = await s.run_async(period="morning", disable_remote_inference = True); print(result.select("answer.q0").first())
+        >>> async def test_run_async(): result = await s.run_async(period="morning", disable_remote_inference = True, disable_remote_cache=True); print(result.select("answer.q0").first())
         >>> asyncio.run(test_run_async())
         yes
         >>> import asyncio
@@ -887,20 +931,23 @@ class Survey(SurveyExportMixin, Base):
         >>> def f(scenario, agent_traits): return "yes" if scenario["period"] == "morning" else "no"
         >>> q = QuestionFunctional(question_name = "q0", func = f)
         >>> s = Survey([q])
-        >>> async def test_run_async(): result = await s.run_async(period="evening", disable_remote_inference = True); print(result.select("answer.q0").first())
-        >>> asyncio.run(test_run_async())
+        >>> async def test_run_async(): result = await s.run_async(period="evening", disable_remote_inference = True, disable_remote_cache = True); print(result.select("answer.q0").first())
+        >>> results = asyncio.run(test_run_async())
         no
         """
         # TODO: temp fix by creating a cache
         if cache is None:
             from edsl.data import Cache
-
             c = Cache()
         else:
             c = cache
-        jobs: "Jobs" = self.get_job(model=model, agent=agent, **kwargs)
+
+        
+
+        jobs: "Jobs" = self.get_job(model=model, agent=agent, **kwargs).using(c)
         return await jobs.run_async(
-            cache=c, disable_remote_inference=disable_remote_inference
+            disable_remote_inference=disable_remote_inference,
+            disable_remote_cache=disable_remote_cache,
         )
 
     def run(self, *args, **kwargs) -> "Results":
@@ -918,6 +965,12 @@ class Survey(SurveyExportMixin, Base):
 
         return Jobs(survey=self).run(*args, **kwargs)
 
+    def using(self, obj: Union["Cache", "KeyLookup", "BucketCollection"]) -> "Jobs":
+        """Turn the survey into a Job and appends the arguments to the Job."""
+        from edsl.jobs.Jobs import Jobs
+
+        return Jobs(survey=self).using(obj)
+
     def duplicate(self):
         """Duplicate the survey.
 
@@ -1086,7 +1139,7 @@ class Survey(SurveyExportMixin, Base):
         # questions_string = ", ".join([repr(q) for q in self._questions])
         questions_string = ", ".join([repr(q) for q in self.raw_passed_questions or []])
         # question_names_string = ", ".join([repr(name) for name in self.question_names])
-        return f"Survey(questions=[{questions_string}], memory_plan={self.memory_plan}, rule_collection={self.rule_collection}, question_groups={self.question_groups})"
+        return f"Survey(questions=[{questions_string}], memory_plan={self.memory_plan}, rule_collection={self.rule_collection}, question_groups={self.question_groups}, questions_to_randomize={self.questions_to_randomize})"
 
     def _summary(self) -> dict:
         return {
@@ -1172,7 +1225,7 @@ class Survey(SurveyExportMixin, Base):
 
     def get_job(self, model=None, agent=None, **kwargs):
         if model is None:
-            from edsl.language_models.registry import Model
+            from edsl.language_models.model import Model
 
             model = Model()
 
@@ -1193,26 +1246,24 @@ def main():
 
     def example_survey():
         """Return an example survey."""
-        from edsl.questions.QuestionMultipleChoice import QuestionMultipleChoice
-        from edsl.surveys.Survey import Survey
+        from edsl import QuestionMultipleChoice, QuestionList, QuestionNumerical, Survey
 
         q0 = QuestionMultipleChoice(
-            question_text="Do you like school?",
-            question_options=["yes", "no"],
             question_name="q0",
+            question_text="What is the capital of France?",
+            question_options=["London", "Paris", "Rome", "Boston", "I don't know"]
         )
-        q1 = QuestionMultipleChoice(
-            question_text="Why not?",
-            question_options=["killer bees in cafeteria", "other"],
+        q1 = QuestionList(
             question_name="q1",
+            question_text="Name some cities in France.",
+            max_list_items = 5
         )
-        q2 = QuestionMultipleChoice(
-            question_text="Why?",
-            question_options=["**lack*** of killer bees in cafeteria", "other"],
+        q2 = QuestionNumerical(
             question_name="q2",
+            question_text="What is the population of {{ q0.answer }}?"
         )
         s = Survey(questions=[q0, q1, q2])
-        s = s.add_rule(q0, "q0 == 'yes'", q2)
+        s = s.add_rule(q0, "q0 == 'Paris'", q2)
         return s
 
     s = example_survey()

edsl/test_h

@@ -0,0 +1 @@
+[{'model_name': 'nvidia/Nemotron-4-340B-Instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Nemotron-4-340B-Instruct is a chat model intended for use for the English language, designed for Synthetic Data Generation', 'cover_img_url': 'https://shared.deepinfra.com/models/nvidia/Nemotron-4-340B-Instruct/cover_image.6223332b8dfbf8dba008d030548970e7dbee4cfb571412430cc5ff8c007b7072.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'meta-llama/Llama-2-7b-chat-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. ', 'cover_img_url': 'https://shared.deepinfra.com/models/meta-llama/Llama-2-7b-chat-hf/cover_image.10373e7a429dd725e0eb9e57cd20aeb815426c077217b27d9aedce37bd5c2173.jpg', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'meta-llama/Meta-Llama-3-8B-Instruct', 'deprecated': 1718309480, 'quantization': 'fp16'}, {'model_name': 'meta-llama/Llama-2-13b-chat-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. ', 'cover_img_url': 'https://shared.deepinfra.com/models/meta-llama/Llama-2-13b-chat-hf/cover_image.6cbca6a3445de3ac6e75983f8828fe6b6323ae8a2d3c025ae1561ac5e56e6326.jpg', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'meta-llama/Meta-Llama-3-8B-Instruct', 'deprecated': 1718228019, 'quantization': 'fp16'}, {'model_name': 'deepinfra/airoboros-70b', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Latest version of the Airoboros model fine-tunned version of llama-2-70b using the Airoboros dataset. This model is currently running jondurbin/airoboros-l2-70b-2.2.1 ', 'cover_img_url': 'https://shared.deepinfra.com/models/deepinfra/airoboros-70b/cover_image.4df6a78233488497ec8cad9a032e070a1c2e0c510c7d3b2ebd5c159e15b69793.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'lizpreciatior/lzlv_70b_fp16_hf', 'deprecated': 1718067221, 'quantization': 'fp16'}, {'model_name': '01-ai/Yi-34B-Chat', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': '', 'cover_img_url': 'https://shared.deepinfra.com/models/01-ai/Yi-34B-Chat/cover_image.ba50c187d0414ba799d008eef1756d102f2a016b33109023a5d05ac7370f21c8.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'cognitivecomputations/dolphin-2.6-mixtral-8x7b', 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'mistralai/Mistral-7B-Instruct-v0.2', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.2 generative text model using a variety of publicly available conversation datasets.', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.2/cover_image.429fef8a2a09e5c4104ede511db12beaea9d3917c4754d709b05a65d5d6f6c1f.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'Qwen/Qwen2-7B-Instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The 7 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.', 'cover_img_url': 'https://shared.deepinfra.com/models/Qwen/Qwen2-7B-Instruct/cover_image.e8c2257ba46edbd20ef17c81343ad40fdf27f7bc3838837d079557accd2879e2.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'Qwen/Qwen2-72B-Instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The 72 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.', 'cover_img_url': 'https://shared.deepinfra.com/models/Qwen/Qwen2-72B-Instruct/cover_image.6771b7ff122c6ffaa9d5ae6b6ab54db0d46079a8f90441fa7770d60cfd4c6f4f.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'google/codegemma-7b-it', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'CodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.', 'cover_img_url': 'https://shared.deepinfra.com/models/google/codegemma-7b-it/cover_image.ecf88bf320526e3a113a1e51057501ffe65b8e264912e0c920ae7f95553f74b2.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': 'google/gemma-1.1-7b-it', 'deprecated': 1718830428, 'quantization': 'fp16'}, {'model_name': 'mistralai/Mistral-7B-Instruct-v0.3', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Mistral-7B-Instruct-v0.3 is an instruction-tuned model, next iteration of of Mistral 7B that has larger vocabulary, newer tokenizer and supports function calling.', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.3/cover_image.716d64cdc98717436953bde0b80dede06d7071f66cb46f1df85caaa270e5cdd6.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'mistralai/Mixtral-8x7B-Instruct-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Mixtral is mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 7b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks.', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mixtral-8x7B-Instruct-v0.1/cover_image.a3146cc88bb3c77e6eae14b35d8db03d7952a597633a53378ef8182186c5a9d7.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'openchat/openchat_3.5', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'OpenChat is a library of open-source language models that have been fine-tuned with C-RLFT, a strategy inspired by offline reinforcement learning. These models can learn from mixed-quality data without preference labels and have achieved exceptional performance comparable to ChatGPT. The developers of OpenChat are dedicated to creating a high-performance, commercially viable, open-source large language model and are continuously making progress towards this goal.', 'cover_img_url': 'https://shared.deepinfra.com/models/openchat/openchat_3.5/cover_image.6112a8e07a704c30bd7c354351fa79c13904d9df7667a0064fb6b30bc80e728b.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'bigcode/starcoder2-15b-instruct-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled data from huge and proprietary LLMs.', 'cover_img_url': 'https://shared.deepinfra.com/models/bigcode/starcoder2-15b-instruct-v0.1/cover_image.f20836d5d430a93c8aa95eefc92154d14e93dc69b17967410ecce3187a07c601.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': None, 'replaced_by': 'Phind/Phind-CodeLlama-34B-v2', 'deprecated': 1718830388, 'quantization': 'fp16'}, {'model_name': 'mistralai/Mistral-7B-Instruct-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.1/cover_image.cdb70679749ff93eb56b8480215bb8cd1382cbeffcec00a06bdb0145be9ef511.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'meta-llama/Meta-Llama-3-8B-Instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.', 'cover_img_url': 'https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3-8B-Instruct/cover_image.9ea753fd36aabfbca4939ee488b859e08e95c4626ffff71ec3a385be66b1d3ba.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'codellama/CodeLlama-34b-Instruct-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Code Llama is a state-of-the-art LLM capable of generating code, and natural language about code, from both code and natural language prompts. This particular instance is the 34b instruct variant', 'cover_img_url': 'https://shared.deepinfra.com/models/codellama/CodeLlama-34b-Instruct-hf/cover_image.6b78b2c46fdafdd29a6eb2bcc388412b0afea3f4286d5ac90ab3c65e2da61be7.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'Phind/Phind-CodeLlama-34B-v2', 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Zephyr 141B-A35B is an instruction-tuned (assistant) version of Mixtral-8x22B. It was fine-tuned on a mix of publicly available, synthetic datasets. It achieves strong performance on chat benchmarks.', 'cover_img_url': 'https://shared.deepinfra.com/models/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/cover_image.06f8e4df28f71df5ed7d0f5c995f296ca5e259f6c9b3a3e8914ba58805fb83a6.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 65536, 'replaced_by': 'mistralai/Mixtral-8x22B-Instruct-v0.1', 'deprecated': None, 'quantization': 'fp8'}, {'model_name': 'Gryphe/MythoMax-L2-13b-turbo', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Faster version of Gryphe/MythoMax-L2-13b running on multiple H100 cards in fp8 precision. Up to 160 tps. ', 'cover_img_url': 'https://shared.deepinfra.com/models/Gryphe/MythoMax-L2-13b-turbo/cover_image.1975a8dba4bcf6809a083fe29aff31cb2895a749171f89e0db650bc039da051a.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'Gryphe/MythoMax-L2-13b', 'deprecated': 1718830497, 'quantization': 'fp8'}, {'model_name': 'codellama/CodeLlama-70b-Instruct-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'CodeLlama-70b is the largest and latest code generation from the Code Llama collection. ', 'cover_img_url': 'https://shared.deepinfra.com/models/codellama/CodeLlama-70b-Instruct-hf/cover_image.6fc1f8b121f95b8075d0bff6f5d6fe39fdac93454078d88467697abe8ecd416b.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'Phind/Phind-CodeLlama-34B-v2', 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'microsoft/WizardLM-2-8x22B', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to those leading proprietary models.", 'cover_img_url': 'https://shared.deepinfra.com/models/microsoft/WizardLM-2-8x22B/cover_image.395b63e0d661def89bf43c88976a699b066f69208b3b58ae5cc2663693033ee8.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 65536, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'databricks/dbrx-instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'DBRX is an open source LLM created by Databricks. It uses mixture-of-experts (MoE) architecture with 132B total parameters of which 36B parameters are active on any input. It outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7B on standard industry benchmarks for language understanding, programming, math, and logic.', 'cover_img_url': 'https://shared.deepinfra.com/models/databricks/dbrx-instruct/cover_image.061dbf63fed77872a3f1b97053081189ceefa2d6fafdc912d2d74111cfbd75c0.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': 'cognitivecomputations/dolphin-2.6-mixtral-8x7b', 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'microsoft/WizardLM-2-7B', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': "WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger open-source leading models", 'cover_img_url': 'https://shared.deepinfra.com/models/microsoft/WizardLM-2-7B/cover_image.305876b2901f4833a14d17e09a3876b59ca7561b73017518970a75643fe9ff69.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'mistralai/Mixtral-8x22B-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Mixtral-8x22B is the latest and largest mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 22b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference.  This model is not instruction tuned. ', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mixtral-8x22B-v0.1/cover_image.eb92d1199149a5d7fa5e7b2dc17dc991f7398301747b92bd60032c3b7fc77a0f.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 65536, 'replaced_by': 'mistralai/Mixtral-8x22B-Instruct-v0.1', 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'mistralai/Mixtral-8x22B-Instruct-v0.1', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI. This state of the art machine learning model uses a mixture 8 of experts (MoE) 22b models. During inference 2 experts are selected. This architecture allows large models to be fast and cheap at inference.', 'cover_img_url': 'https://shared.deepinfra.com/models/mistralai/Mixtral-8x22B-Instruct-v0.1/cover_image.8bb1b015367a1537fd23c69d5b8117675a86b207c9bd3cce326b750ef877bcb6.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 65536, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'meta-llama/Llama-2-70b-chat-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.', 'cover_img_url': 'https://shared.deepinfra.com/models/meta-llama/Llama-2-70b-chat-hf/cover_image.7b3407408b20bd422edfb75da90ee92d0a05649e94b59bf409c827e845fc3c46.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': 'meta-llama/Meta-Llama-3-70B-Instruct', 'deprecated': 1718309527, 'quantization': 'fp16'}, {'model_name': 'google/gemma-1.1-7b-it', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Gemma is an open-source model designed by Google. This is Gemma 1.1 7B (IT), an update over the original instruction-tuned Gemma release. Gemma 1.1 was trained using a novel RLHF method, leading to substantial gains on quality, coding capabilities, factuality, instruction following and multi-turn conversation quality.', 'cover_img_url': 'https://shared.deepinfra.com/models/google/gemma-1.1-7b-it/cover_image.18ce701e05fe6377f27c31c2e0d05649b7962f184f8dc894e31aad3ffb468f70.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'Gryphe/MythoMax-L2-13b', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': '', 'cover_img_url': 'https://shared.deepinfra.com/models/Gryphe/MythoMax-L2-13b/cover_image.7567613d62f797fa930227a88202f7aee5ef30da38e6c9c7b775979cc71220bc.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'openchat/openchat-3.6-8b', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Openchat 3.6 is a LLama-3-8b fine tune that outperforms it on multiple benchmarks.', 'cover_img_url': 'https://shared.deepinfra.com/models/openchat/openchat-3.6-8b/cover_image.c5792073e4034a0847ff5112e00356adb411c4a5c900ed22c32ad65c5d97e8d1.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'Austism/chronos-hermes-13b-v2', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'This offers the imaginative writing style of chronos while still retaining coherency and being capable. Outputs are long and utilize exceptional prose. Supports a maxium context length of 4096. The model follows the Alpaca prompt format.', 'cover_img_url': '', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'Phind/Phind-CodeLlama-34B-v2', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Phind-CodeLlama-34B-v2 is an open-source language model that has been fine-tuned on 1.5B tokens of high-quality programming-related data and achieved a pass@1 rate of 73.8% on HumanEval. It is multi-lingual and proficient in Python, C/C++, TypeScript, Java, and more. It has been trained on a proprietary dataset of instruction-answer pairs instead of code completion examples.  The model is instruction-tuned on the Alpaca/Vicuna format to be steerable and easy-to-use. It accepts the Alpaca/Vicuna instruction format and can generate one completion for each prompt.', 'cover_img_url': 'https://shared.deepinfra.com/models/Phind/Phind-CodeLlama-34B-v2/cover_image.0d7cb500b84d00e46b7bf490b75cf8eda73a3ad775fa4360c8deba541c3349b3.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'lizpreciatior/lzlv_70b_fp16_hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'A Mythomax/MLewd_13B-style merge of selected 70B models  A multi-model merge of several  LLaMA2 70B finetunes for roleplaying and creative work. The goal was to create a model that combines creativity with intelligence for an enhanced experience.', 'cover_img_url': 'https://shared.deepinfra.com/models/lizpreciatior/lzlv_70b_fp16_hf/cover_image.2bb893141f7dce176afce500c4ec8ca22cfe5e2b00253d997fea31a7f60adc1b.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'cognitivecomputations/dolphin-2.6-mixtral-8x7b', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The Dolphin 2.6 Mixtral 8x7b model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat.', 'cover_img_url': 'https://shared.deepinfra.com/models/cognitivecomputations/dolphin-2.6-mixtral-8x7b/cover_image.b265207e1a422c62c06f23a86e6ef6e8ee326de40a24bb1c5d9f102c1f2acd6b.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 32768, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'bigcode/starcoder2-15b', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'StarCoder2-15B model is a 15B parameter model trained on 600+ programming languages. It specializes in code completion.', 'cover_img_url': 'https://shared.deepinfra.com/models/bigcode/starcoder2-15b/cover_image.8981f6e7c85d72bf816c2abcb90d811c905db812ce0560ba5216df8cbc314464.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 16384, 'replaced_by': 'Phind/Phind-CodeLlama-34B-v2', 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'llava-hf/llava-1.5-7b-hf', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'LLaVa is a multimodal model that supports vision and language models combined.', 'cover_img_url': 'https://shared.deepinfra.com/models/llava-hf/llava-1.5-7b-hf/cover_image.ed4fba7a25b147e7fe6675e9f760585e11274e8ee72596e6412447260493cd4f.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'fp16'}, {'model_name': 'meta-llama/Meta-Llama-3-70B-Instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'Model Details Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.', 'cover_img_url': 'https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3-70B-Instruct/cover_image.bcffae761540e7dd36aea32e2a576690d43592a0fc39b9edbe83a5420758aabf.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 8192, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}, {'model_name': 'microsoft/Phi-3-medium-4k-instruct', 'type': 'text-generation', 'reported_type': 'text-generation', 'description': 'The Phi-3-Medium-4K-Instruct is a powerful and lightweight language model with 14 billion parameters, trained on high-quality data to excel in instruction following and safety measures. It demonstrates exceptional performance across benchmarks, including common sense, language understanding, and logical reasoning, outperforming models of similar size.', 'cover_img_url': 'https://shared.deepinfra.com/models/microsoft/Phi-3-medium-4k-instruct/cover_image.6c7f810d3584719025ba43de13448d318bda84043a08af1b9718c61d9498b18c.webp', 'tags': [...], 'pricing': {...}, 'max_tokens': 4096, 'replaced_by': None, 'deprecated': None, 'quantization': 'bfloat16'}]

edsl/utilities/gcp_bucket/example.py

@@ -0,0 +1,50 @@
+from edsl.utilities.gcp_bucket.cloud_storage import CloudStorageManager
+
+# API URLs
+secret_token = "your-secret-token"
+
+# File paths and names
+upload_file_path = "./app.py"
+upload_file_name = "new_upload.py"
+
+# Initialize CloudStorageManager
+manager = CloudStorageManager(secret_token=secret_token) # secret_token only for upload operations
+
+# Upload Process
+try:
+    manager.upload_file(upload_file_path, upload_file_name)
+    print("File upload process completed.")
+except Exception as e:
+    print(f"Upload error: {str(e)}")
+
+# Download Process
+file_name = "new_upload.py"  # Name for the downloaded file
+save_name = "res_download.py"
+try:
+    manager.download_file(file_name, save_name)
+    print("File download process completed.")
+except Exception as e:
+    print(f"Download error: {str(e)}")
+
+# List files
+try:
+    print("listing files")
+    out = manager.list_files()
+    for x in out["data"]:
+        print(f"file_name: {x['file_name']}", f"url: {x['url']}")
+except Exception as e:
+    print(f"Exception in listing files", str(e))
+
+# Delete file
+try:
+    manager.delete_file("new_upload.py")
+except Exception as e:
+    print(f"Exception in deleting file", str(e))
+# List files
+try:
+    print("listing files")
+    out = manager.list_files()
+    for x in out["data"]:
+        print(f"file_name: {x['file_name']}", f"url: {x['url']}")
+except Exception as e:
+    print(f"Exception in listing files", str(e))

{edsl-0.1.39.dev2.dist-info → edsl-0.1.39.dev4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edsl
-Version: 0.1.39.dev2
+Version: 0.1.39.dev4
 Summary: Create and analyze LLM-based surveys
 Home-page: https://www.expectedparrot.com/
 License: MIT
@@ -107,5 +107,5 @@ See instructions on [storing API keys](https://docs.expectedparrot.com/en/latest
 
 ## 💡 Contributions, feature requests & bugs
 Interested in contributing? Want us to add a new feature? Found a bug for us to squash? 
-Please send us an email at [info@expectedparrot.com](mailto:info@expectedparrot.com) or message us at our [Discord channel](https://discord.com/invite/mxAYkjfy9m).
+Please send us an email at [info@expectedparrot.com](mailto:info@expectedparrot.com) or message us at our [Discord channel](https://discord.com/invite/mxAYkjfy9m)..