metadata
library_name: peft
base_model: Locutusque/TinyMistral-248M-Instruct
datasets:
- Locutusque/InstructMix
language:
- en
pipeline_tag: text-generation
widget:
- text: >-
<|ASSISTANT|> Here is a possible solution to transform high haircare
styling and trimming based on decision making for professionals
incorporating `if`/`else` statements to handle different consent
scenarios: 1. Define nodes and relationships for the graph database:
```cypher CREATE (client:Client) CREATE (stylist:Stylist)-[:HAS_CLIENT
{start_date: date() }]->(client) // Relationship types used in this query
MATCH (s:Service), (c:Client) WHERE s.name = 'Haircut' AND c IN [client]
MERGE (s)<-[r:CONFIRMS_SERVICE]-(c); // Other relationship types could
also be added here as needed ``` 2. Query to determine whether client has
given their explicit consent to receive specific services: ```cypher //
Get all services provided by stylists to clients MATCH
(s:Stylist)-[r:PROVIDES_SERVICE*0..5]-(:Service) WITH collect(distinct s)
AS stylists, r UNWIND stylists AS s OPTIONAL MATCH
(c:Client)-[:HAS_CLIENT]->(sc:ServiceConsent{service:r}) RETURN s,
count(*), sum(CASE WHEN sc IS NOT NULL THEN 1 ELSE 0 END) AS num_consents
ORDER BY num_consents DESC; ``` 3. Example of how to use the above query
to check which service a particular client has already agreed to:
```cypher // Check if client has previously granted consent to any
services MATCH (s:Stylist)-[r:PROVIDES_SERVICE*0..5]-(:Service) WITH
collect(distinct s) AS stylists, r UNWIND stylists AS s OPTIONAL MATCH
(c:Client)-[:HAS_CLIENT]->(sc:ServiceConsent{service:r}) WHERE id(c) = <id
of client> RETURN s, count(*), sum(CASE WHEN sc IS NOT NULL THEN 1 ELSE 0
END) AS num_consents; ``` 4. Code to add new consent for a new service:
```cypher // Add new consent for a new service MERGE (c:Client {id: '<id
of client>'}) ON CREATE SET c.created_at=timestamp(),
c.updated_at=timestamp() MERGE (s:Service {name: '<new service name>'}) ON
CREATE SET s.created_at=timestamp(), s.updated_at=timestamp() MERGE
(c)-[:GIVEN_SERVICE_CONSENT {consent_given: true}]->(sc:ServiceConsent
{service: s}); ``` 5. Code to update existing consent for an existing
service: ```cypher // Update existing consent for an existing service
MATCH (c:Client {id: '<id of client>'}), (s:Service {name: '<existing
service name>'}) MERGE (c)-[:GIVEN_SERVICE_CONSENT {consent_given:
false}]->(oldSc:ServiceConsent) MERGE (c)-[:GIVEN_SERVICE_CONSENT
{consent_given: true}]->(newSc:ServiceConsent {service: s}); DELETE oldSc;
``` 6. Code to delete consent for a service: ```cypher // Delete consent
for a service MATCH (c:Client {id: '<id of client>'}), (s:Service {name:
'<service name>'}) REMOVE (c)-[:GIVEN_SERVICE_CONSENT {consent_given:
true}]->(sc:ServiceConsent {service: s}); ``` This approach usesNeo4j's
native cypher language to define the database schema and perform queries
and mutations on the graph. <|USER|>
inference:
parameters:
temperature: 0.8
do_sample: true
top_p: 0.14
top_k: 41
max_new_tokens: 250
repetition_penalty: 1.176
Uses
This model is intended to be used to create instruction-following datasets by predicting a question by passing an answer to it.
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- 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]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[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: QuantizationMethod.BITS_AND_BYTES
- 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: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.2